CN113688202B - Emotion polarity analysis method and device, electronic equipment and computer storage medium - Google Patents
Emotion polarity analysis method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113688202B CN113688202B CN202110868892.7A CN202110868892A CN113688202B CN 113688202 B CN113688202 B CN 113688202B CN 202110868892 A CN202110868892 A CN 202110868892A CN 113688202 B CN113688202 B CN 113688202B
- Authority
- CN
- China
- Prior art keywords
- emotion
- polarity
- emotion polarity
- nodes
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000008451 emotion Effects 0.000 title claims abstract description 789
- 238000004458 analytical method Methods 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 claims abstract description 60
- 238000004364 calculation method Methods 0.000 claims abstract description 49
- 230000003542 behavioural effect Effects 0.000 claims abstract description 26
- 230000006399 behavior Effects 0.000 claims description 102
- 230000008569 process Effects 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 description 26
- 238000005516 engineering process Methods 0.000 description 14
- 238000003058 natural language processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 5
- 238000012804 iterative process Methods 0.000 description 4
- 230000002996 emotional effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the application provides an emotion polarity analysis method, an emotion polarity analysis device, electronic equipment and a computer readable storage medium, and relates to the technical field of computers. The method comprises the following steps: determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node with a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value; acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished; and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes. Therefore, by implementing the method, the emotion polarity values of all the nodes are obtained through calculation, and the efficiency of determining the emotion polarity analysis result of the object to be reviewed is improved.
Description
Technical Field
Embodiments of the present application relate to the field of computer technology, and more particularly, to an emotion polarity analysis method, an emotion polarity analysis device, an electronic apparatus, and a computer-readable storage medium.
Background
This section is intended to provide a background or context to the embodiments of the disclosure recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
At present, with the development of computer technology, users can comment on some information displayed in a terminal, or perform actions with emotion tendencies such as praise, collection and the like on the information, and the accuracy of a follow-up recommendation system can be improved by analyzing comments issued by the users and emotion tendencies of the users on the information. However, in the related art, the text information in the information is generally classified by using a natural language processing technology to identify the emotion tendencies, and because the identified text information is a short text and is irrelevant to the context in the identification process, the accuracy of emotion tendencies identification is reduced, and the application scene of emotion tendencies identification is reduced.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute a related art known to those of ordinary skill in the art.
Disclosure of Invention
Based on the above problems, the inventor carries out corresponding thinking and makes pointed improvement, and provides an emotion polarity analysis method, an emotion polarity analysis device, electronic equipment and a computer readable storage medium, wherein a node for determining an emotion polarity value is selected as a seed node, the emotion polarity value of a first object node with a first action association relationship with the seed node is determined by taking the seed node as a starting point, the emotion polarity value of a first object emotion node and the emotion polarity value of a second action association relationship are utilized to determine emotion polarity values of other nodes, so that the emotion polarity analysis result of an object to be reviewed is determined, the social network information and a natural language processing technology capable of only identifying short text information are prevented from being used in the process of determining the emotion polarity analysis result, and the accuracy and efficiency of the determined emotion polarity analysis result are improved.
According to a first aspect of an embodiment of the present application, a method for emotion polarity analysis is disclosed, including:
Determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node with a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value;
acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished;
and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes.
In one embodiment, based on the foregoing scheme, determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relationship and the emotion polarity value of the first object node includes:
acquiring a first behavioral emotion polarity value corresponding to the first behavioral association relationship, and calculating to obtain an emotion polarity value of the first object node according to the first behavioral emotion polarity value and the emotion polarity value of the seed node;
Determining a second behavior emotion polarity value corresponding to the second behavior association relation, and calculating the second behavior emotion polarity value and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration.
In one embodiment, based on the foregoing scheme, the first object node comprises a user node and the second object node comprises a comment node;
the calculating the emotion polarity value of the second behavior and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration, including:
when second behavior association relations are established between the evaluation node and the user nodes respectively, polarity calculation weights and emotion polarity values corresponding to the user nodes respectively are obtained;
and calculating to obtain the emotion polarity value of the evaluation node according to the second behavior polarity value corresponding to all the second behavior association relations, the polarity calculation weight corresponding to all the user nodes and the emotion polarity value.
In one embodiment, based on the foregoing scheme, determining, at the end of the iteration, the emotion polarity analysis result of the object to be reviewed according to emotion polarity values of all nodes includes:
Determining emotion polarity values of all nodes at the end of iteration, and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value;
if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, calculating polarity difference values between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value respectively;
and determining the emotion polarities of all the nodes according to the polarity difference value, and determining the emotion polarity analysis result of the object to be evaluated according to the emotion polarities of all the nodes.
In one embodiment, based on the foregoing scheme, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarities of all the nodes includes:
respectively counting the number of the nodes with positive emotion polarities and the number of the nodes with negative emotion polarities to obtain positive emotion statistical results and negative emotion statistical results;
calculating positive emotion polarity duty ratio and negative emotion polarity duty ratio according to the positive emotion statistical result and the negative emotion statistical result;
If the positive emotion polarity duty ratio is larger than the negative emotion polarity duty ratio, or the positive emotion statistical result is larger than or equal to a polarity number threshold value, determining that the emotion polarity analysis result of the object to be commented is a positive emotion polarity result;
and if the positive emotion polarity proportion is smaller than the negative emotion polarity proportion, or the negative emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is a negative emotion polarity analysis result.
In one embodiment, based on the foregoing scheme, the method further comprises:
and determining the user node with the forward emotion polarity, and recommending the object to be reviewed and/or other objects to be reviewed similar to the object to be reviewed to the user corresponding to the user node.
In one embodiment, based on the foregoing scheme, determining, at the end of the iteration, the emotion polarity analysis result of the object to be reviewed according to emotion polarity values of all nodes includes:
acquiring preset iteration ending times, and determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of the nodes if the iteration times corresponding to the current iteration reach the preset iteration ending times; or (b)
Determining current iteration emotion polarity values of all nodes corresponding to the current iteration, and determining adjacent iteration emotion polarity values of all nodes in an adjacent iteration process; wherein the adjacent iteration process is an iteration process having an iteration sequence relation with the current iteration;
and calculating the polarity updating value of the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determining the emotion analysis result of the object to be reviewed according to the emotion polarity values of all nodes if the polarity updating value is smaller than or equal to a preset polarity change threshold value.
According to a second aspect of embodiments of the present application, there is disclosed an emotion polarity analysis device, including: the system comprises an acquisition unit, an iteration unit and an emotion polarity analysis module, wherein:
the system comprises an acquisition unit, a first operation unit and a second operation unit, wherein the acquisition unit is used for determining an emotion polarity value of a seed node corresponding to an object to be reviewed and acquiring a first object node with a first behavior association relation with the seed node; the seed node is a node for determining the emotion polarity value;
the iteration unit is used for acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished;
And the emotion polarity analysis unit is used for determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of all nodes when the iteration is finished.
According to a third aspect of embodiments of the present application, an electronic device is disclosed, comprising: a processor; and a memory having stored thereon computer readable instructions which, when executed by the processor, implement the emotion polarity analysis method as disclosed in the first aspect.
According to a fourth aspect of embodiments of the present application, a computer program medium is disclosed, on which computer readable instructions are stored which, when executed by a processor of a computer, cause the computer to perform the emotion polarity analysis method disclosed according to the first aspect of the present application.
According to the method and the device, the emotion polarity value of the seed node corresponding to the object to be commented can be determined, and the first object node with the first behavior association relation with the seed node is obtained; the seed node is a node for determining the emotion polarity value; acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished; and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes. Compared with the related art, the embodiment of the application is implemented, on one hand, the node for determining the emotion polarity value is selected as the seed node, the emotion polarity value of the first object node with the first action association relation with the seed node is determined by taking the node as the starting point, the emotion polarity value of the first object emotion node and the emotion polarity value of other nodes are determined by utilizing the emotion polarity value of the first object emotion node and the second action association relation, so that the emotion polarity analysis result of the object to be commented is determined, the social network information and the natural language processing technology which can only identify the short text information are prevented from being used in the process of determining the emotion polarity analysis result, the accuracy and the efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged; on the other hand, the emotion polarity values of all the nodes are obtained according to calculation, so that the complexity of determining the emotion polarity analysis result of the object to be reviewed is reduced, and the efficiency of determining the emotion polarity analysis result of the object to be reviewed is further improved.
Other features and advantages of the present application will be apparent from the following detailed description, or may be learned in part by the practice of the application.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:
FIG. 1 is a flow chart of a method of emotion polarity analysis according to an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram illustrating the structure of all nodes corresponding to Song A according to an example embodiment of the present application;
FIG. 3 is a schematic diagram illustrating the structure of all nodes corresponding to Song B according to an example embodiment of the present application;
FIG. 4 is a flow chart illustrating the determination of emotion polarity values for a second object node in a current iteration according to an exemplary embodiment of the present application;
FIG. 5 is a flowchart of obtaining an emotion polarity value of a second object node in a current iteration according to an exemplary embodiment of the present application;
FIG. 6 is a flowchart illustrating a determination of emotion polarity analysis results for an object to be reviewed according to an example embodiment of the present application;
FIG. 7 is a flowchart illustrating a determination of emotion polarity analysis results for an object to be reviewed according to an example embodiment of the present application;
FIG. 8 is a flowchart illustrating the determination of the emotion polarity analysis result of an object to be reviewed according to emotion polarity values of all nodes at the end of an iteration according to an exemplary embodiment of the present application;
FIG. 9 is a block diagram showing the structure of an emotion polarity analysis device according to another alternative exemplary embodiment of the present application;
FIG. 10 is a block diagram illustrating a emotion polarity analysis electronic device in accordance with another alternative example embodiment of the present application.
In the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Detailed Description
The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are presented merely to enable one skilled in the art to better understand and practice the present application and are not intended to limit the scope of the present application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be appreciated by those skilled in the art that embodiments of the present application may be embodied as an apparatus, device, method or computer program product. Thus, the present application may be embodied in the form of: complete hardware, complete software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
According to an embodiment of the present application, there are provided an emotion polarity analysis method, an emotion polarity analysis device, an electronic apparatus, and a computer-readable storage medium.
Any number of elements in the figures are for illustration and not limitation, and any naming is used for distinction only and not for any limiting sense.
The principles and spirit of the present application are explained in detail below with reference to several representative embodiments thereof.
Summary of The Invention
At present, the scheme of emotion polarity analysis in the related art is generally as follows: and classifying the text information by adopting a natural language processing technology alone or adopting a mode of combining the natural language processing technology and the social network information so as to obtain an emotion polarity analysis result. Therefore, the emotion polarity analysis result by the method is generally a result obtained by identifying short text information, and the correlation degree between social network information and comments issued by users is low, so that the application scene of the emotion polarity analysis result is reduced, the accuracy of the emotion polarity analysis result is reduced, and the efficiency of determining the emotion polarity analysis result is reduced.
Based on the above-mentioned problems, the applicant thinks that natural language processing technology and social network information can be avoided in the emotion polarity analysis process, and in one embodiment of the disclosure, an emotion polarity value of a seed node corresponding to an object to be reviewed is determined, and a first object node having a first behavioral association relationship with the seed node is obtained; the seed node is a node for determining the emotion polarity value; acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished; and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes. Therefore, the node for determining the emotion polarity value is selected as the seed node, the emotion polarity value of the first object node with the first action association relation with the seed node is determined by taking the node as the starting point, the emotion polarity value of the first object emotion node and the emotion polarity value of other nodes are determined by utilizing the emotion polarity value of the first object emotion node and the second action association relation, so that the emotion polarity analysis result of the object to be commented is determined, the social network information and the natural language processing technology which can only identify short text information are prevented from being used in the process of determining the emotion polarity analysis result, the accuracy and the efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged.
Application scene overview
It should be noted that the following application scenario is only shown for the convenience of understanding the spirit and principles of the present application, and embodiments of the present application are not limited in any way in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
When the method is applied to the emotion polarity analysis scene, the social network information and the natural language processing technology which can only identify short text information are used in the process of determining the emotion polarity analysis result in the related technology, the accuracy and the efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged.
Exemplary method
The emotion polarity analysis method according to an exemplary embodiment of the present application will be described below with reference to fig. 1 and 10 in conjunction with the above application scenario.
Referring to fig. 1, fig. 1 is a schematic flow chart of an emotion polarity analysis method according to an exemplary embodiment of the present application. As shown in fig. 1, the emotion polarity analysis method may include:
step S110: determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node with a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value.
Step S120: and acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished.
Step S130: and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes.
According to the emotion polarity analysis method shown in FIG. 1, on one hand, a node for determining an emotion polarity value is selected as a seed node, the emotion polarity value of a first object node with a first action association relation with the seed node is determined by taking the node as a starting point, the emotion polarity values of other nodes are determined by utilizing the emotion polarity value of the first object emotion node and a second action association relation, so that the emotion polarity analysis result of an object to be reviewed is determined, the social network information and a natural language processing technology which can only identify short text information are prevented from being used in the process of determining the emotion polarity analysis result, the accuracy and efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged; on the other hand, the emotion polarity values of all the nodes are obtained according to calculation, so that the complexity of determining the emotion polarity analysis result of the object to be reviewed is reduced, and the efficiency of determining the emotion polarity analysis result of the object to be reviewed is further improved.
These steps are described in detail below.
In step S110, determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node having a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value.
Specifically, the object to be reviewed refers to an object that can be reviewed by the user, for example, may be a song, may be an article, may be a video, and the present exemplary embodiment is not limited thereto.
The seed node refers to a node for determining the emotion polarity value in all nodes, wherein all nodes comprise user nodes and comment nodes, if a user node A reports or shields an object to be comment in a plurality of user nodes, the user node A can be determined to be a user with negative emotion of the object to be comment, so that the user node A can be used as a seed node, and user information or comment information represented by all nodes can be input into an emotion recognition model to be used as a seed node.
The emotion polarity value refers to a value reflecting the emotion tendency of the node to the object to be reviewed, if the emotion tendency of the node to the object to be reviewed is positive, the emotion polarity value may be +1, and if the emotion tendency of the node to the object to be reviewed is negative, the emotion polarity value may be-1.
The user node refers to a node formed by users having an emotion behavior relation with the object to be reviewed, the comment node refers to a node formed by comment information of the object to be reviewed, which is posted by the users, the emotion behavior relation refers to a behavior generated by the users represented by the user node for the object to be reviewed, which can reflect the emotion tendency of the object to be reviewed by the users to a certain extent, for example, can be a shielding behavior of the object to be reviewed, can be a reporting behavior of the object to be reviewed, can be a praise behavior of the object to be reviewed, and the exemplary embodiment is not limited in this way.
The first object node refers to a node with a first behavior association relation with the seed node, if the seed node is a user node, the first object node can be a comment node which is praised, reported, shielded or issued by the user, wherein praised, reported, screen or issued is the first behavior association relation; if the seed node is a comment node, the first object node may be a user node that performs praise, report, screen or issue on the comment node, where praise, report, screen or issue is the first behavior association relationship.
For example, fig. 2 shows a schematic structural diagram of all nodes corresponding to a song a, as shown in fig. 2, where all nodes include 5 comment nodes and 5 user nodes, which are respectively comment node a, comment node B, comment node C, comment node D, comment node E, user node 1, user node 2, user node 3, user node 4, and user node 5, and lines with directions in the diagram represent emotion polarity propagation directions, where seed nodes are comment nodes a, comment nodes E, and user nodes 4 for determining emotion tendencies, and based on this, emotion polarity values of comment nodes a, comment nodes E, and user nodes 4 are obtained.
For example, fig. 3 shows a schematic structural diagram of all nodes corresponding to a song B, as shown in fig. 3, where all nodes include 3 comment nodes and 2 user nodes, that is, comment node F, comment node G, comment node H, user node 6, and user node 7, respectively, and connection lines with directions in the figure represent emotion polarity propagation directions, where only one seed node may be, for example, comment node F, and based on this, comment polarity values of comment node F are obtained.
The user node 1 and the user node 3 respectively issue and praise the comment node a, the user node 5 praise the comment node E, and the comment node D is issued by the user node 4, so that the user node 1, the user node 3, the user node 5 and the comment node D are first object nodes.
Therefore, in the present exemplary embodiment, the emotion polarity value of the seed node corresponding to the object to be reviewed is determined, and since the seed node is a point for determining the emotion polarity value, a foundation is laid for determining an accurate emotion polarity analysis result subsequently, and accuracy of the emotion polarity analysis result of the object to be reviewed subsequently determined is improved.
In step S120, a second object node having a second behavior association relationship with the first object node is obtained, and based on the second behavior association relationship and the emotion polarity value of the first object node, the emotion polarity value of the second object node in the current iteration is determined, so that the iteration is continued until the iteration is ended.
Specifically, if the first object node is a user node, the second object node may be a comment node issued, praised, shielded and reported by a user represented by the user node, and the issuing, praised, shielded or reported is the second behavior association relationship.
Based on this, the emotion polarity value of the second object node can be determined according to the second behavior association relationship and the emotion polarity value of the first object node, and continuing until the emotion polarity values of all the nodes are determined, that is, the current iteration process is completed, and it is worth noting that, when the next iteration begins, the determined seed node is different from the seed node determined in the previous iteration process.
For example, as shown in fig. 2, the first object nodes are user node 1, user node 3, user node 5, and comment node D, and based on this, the second object nodes are comment node B, comment node C, comment node D, and user node 2, where comment node D is both the first object node and the second object node, specifically, comment node D is the first object node with respect to user node 4, and comment node D is the second object node with respect to comment node E.
Based on the above, according to the second behavior association relationship and the emotion polarity value of the first object node, determining the emotion polarity values of the comment node B, the comment node C and the user node 2 to finish the iteration, and selecting one or more nodes different from the comment node A, the comment node E and the user node 4 as seed nodes when the next iteration starts, and continuing repeating the steps until the iteration ends.
As an alternative embodiment, please refer to fig. 4, fig. 4 shows a schematic flow chart for determining the emotion polarity value of the second object node in the current iteration. As shown in fig. 4, may include:
step S410: and acquiring a first behavior emotion polarity value corresponding to the first behavior association relation, and calculating to obtain the emotion polarity value of the first object node according to the first behavior emotion polarity value and the emotion polarity value of the seed node.
The first action association relationship may be actions such as praise, release, shielding and reporting, and may reflect emotion tendencies, where praise and release may be regarded as first action association relationship having positive emotion tendencies, shielding and reporting may be regarded as first action association relationship having negative emotion tendencies, based on which the first action emotion polarity value of the first action association relationship having positive emotion tendencies may be represented by positive numbers, and similarly, the first action emotion polarity value of the first action association relationship having negative emotion tendencies may be represented by negative numbers.
For example, as shown in fig. 2, the seed nodes are comment nodes a, comment nodes E and user nodes 4, the emotion polarity value of comment node a is-1, the emotion polarity value of comment node E is +1, the emotion polarity value of user node 4 is-1, and the first object nodes are user nodes 1, 3, 5 and D.
Based on this, since the first behavior association relationship between the user node 1 and the comment node a is a posting, the first behavior emotion polarity value of the first behavior association relationship is +1, since the first behavior association relationship between the user node 3 and the comment node a is a praise, the first behavior association relationship of the first behavior association relationship is +1, and similarly, since the comment represented by the comment node D is a comment posted by the user node 5, the first behavior association relationship is +1, since the user node 5 is a praise with the first behavior association relationship of the comment node D, the first behavior emotion polarity value is +1.
Calculating the emotion polarity value of the first action emotion polarity value and the emotion polarity value of the seed node, so that the emotion polarity value of the user node 1 is minus 1, the emotion polarity value of the user node 3 is minus 1, and the emotion polarity value of the comment node D is minus 1.
Step S420: and determining a second behavior emotion polarity value corresponding to the second behavior association relation, and calculating the second behavior emotion polarity value and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration.
The determining process of the emotion polarity value of the second behavior is the same as that of the first behavior, and similarly, the emotion polarity value of the second behavior and the emotion polarity value of the first object node can be calculated to obtain the emotion polarity value of the second object node.
For example, as shown in fig. 2, the second object node includes comment node B, comment node C and user node 2, and since comment node B is a node that is endorsed by user node 1, the second behavioral emotion polarity value is +1, since comment node C is a node reported by user node 3, the second behavioral emotion polarity value is-1, and since user node 2 is a node that is endorsed by comment node D, the second behavioral emotion polarity value is +1, based on which the emotional polarity value of comment node B is-1, the emotional polarity value of comment node C is +1, and the emotional polarity value of user node 2 is +1.
Therefore, according to the implementation of the alternative embodiment, on one hand, the emotion polarity value of the first object node and the emotion polarity value of the second object node are obtained through calculation, the complexity of the emotion polarity analysis result of the object to be reviewed is reduced, the efficiency of determining the emotion polarity analysis result of the object to be reviewed is further improved, on the other hand, the emotion polarity value of the first behavior emotion polarity value, the emotion polarity value of the second behavior emotion polarity value and the emotion polarity value of the seed node are all values with direct relation with emotion tendencies, the accuracy of determining the emotion polarity analysis result of the object to be reviewed is improved, only the emotion polarity of short text information can not be identified, and the use scene of emotion polarity analysis is enlarged.
As an alternative embodiment, please refer to fig. 5, fig. 5 shows a schematic flow chart of obtaining the emotion polarity value of the second object node in the current iteration. As shown in fig. 5, the first object node includes a user node, and the second object node includes a comment node, which may include:
step S510: and when second behavior association relations are established between the comment nodes and the user nodes respectively, acquiring polarity calculation weights and emotion polarity values corresponding to the user nodes respectively.
Specifically, the polarity calculation weight refers to the influence degree of the user node with the second behavior association relation with the comment node on the emotion polarity value of the comment node in the process of calculating the emotion polarity value of the comment node.
The polarity calculation weight may be determined according to a user class corresponding to the user node, may be determined according to a corresponding weight calculation algorithm, or may be determined according to a difference between an emotion polarity value of the user node and an emotion polarity standard value, which is not particularly limited in this exemplary embodiment, where the emotion polarity standard value refers to a value for measuring emotion tendency represented by an emotion polarity value.
For example, as shown in fig. 2, for comment node D, both user node 2 and user node 5 have a second behavior association relationship with comment node D, and at this time, it is determined that the polarity calculation weight of user node 2 is 1, the polarity calculation weight of node 5 is 1, the emotion polarity value of user node 2 is +1, and the emotion polarity value of user node 5 is +1.
Step S520: and calculating the emotion polarity value of the comment node according to the second behavior polarity value corresponding to all the second behavior association relations, the polarity calculation weight and the emotion polarity value respectively corresponding to all the user nodes.
Specifically, the emotion polarity value of the comment node needs to be calculated according to the polarity calculation weight, the emotion polarity value and the second behavior polarity value.
For example, as shown in fig. 2, comment node D is a node having a specific first behavior association relationship with user node 4, but comment node D has a second behavior association relationship with user node 2 and user node 5, so when calculating the emotion polarity value of comment node D, it is necessary to obtain emotion polarity value +1 of user node 2, polarity calculation weight 1 of user node 2, emotion polarity value +1 of user node 5, and polarity calculation weight 1 of user node 5, so as to obtain the emotion polarity value of comment node D as arithmetic average value 1/3 of user node 2, user node 4, and user node 5, specifically, when calculating emotion polarity value of comment node D, first determine emotion polarity values of user node 4, user node 5, and user node 2, and emotion polarity value-1 corresponding to the praise action of user node 4, emotion polarity value +1 corresponding to the release action of user node 5 and emotion polarity value +1 corresponding to the praise action of user node 5, then multiplying emotion polarity value of user node 4, polarity calculation weight corresponding to user node 4 and emotion polarity value-1 corresponding to the praise action of user node 4 to obtain calculation result A, and so on, performing corresponding calculation on user node 5 and user node 2 to obtain calculation result B and calculation result C, specifically calculation result A is-1, calculation result B and calculation result C is +1, then adding calculation result A, calculation result B and calculation result C to obtain calculation result D, specifically settlement result D is +1, and finally because user node 4 is, the user node 2 and the user node 5 have emotion polarity propagation between the comment nodes D, so that the emotion polarity value +1/3 of the comment node D is obtained by dividing the calculation result D by 3.
Therefore, when the alternative embodiment is implemented, the polarity calculation weight is added when the emotion polarity value of the comment node is calculated, so that factors influencing the emotion polarity value of the comment node are perfected, and the accuracy of the determined emotion polarity value of the comment node is further improved.
In step S130, when the iteration is finished, the emotion polarity analysis result of the object to be reviewed is determined according to the emotion polarity values of all the nodes.
Specifically, the emotion polarity analysis result of the object to be reviewed is an emotion tendency result of the user to be reviewed, that is, whether most users are positive emotion tendency or negative emotion tendency of the object to be reviewed.
For example, at the end of the iteration, if more than half of the nodes for Song A have emotion polarity values with positive emotion tendencies, then it is determined that most users are favoring Song A.
As an alternative embodiment, please refer to fig. 6, fig. 6 shows a schematic flow chart for determining the emotion polarity analysis result of the object to be reviewed. As shown in fig. 6, may include:
step S610: and determining the emotion polarity values of all nodes at the end of iteration, and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value.
Specifically, the positive emotion polarity standard value refers to a value for measuring positive emotion tendency degree of an emotion polarity value, and the negative emotion polarity standard value corresponds to a value for measuring negative emotion tendency degree of an emotion polarity value.
For example, when the iteration is ended, a positive emotion polarity standard value of +1 and a negative emotion polarity standard value of-1 are obtained.
Step S620: if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, respectively calculating polarity difference values between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value.
Specifically, when the emotion polarity value is different from both the positive emotion standard value and the negative emotion standard value, it is proved that the emotion tendency of the emotion is required to be judged at this time so as to determine the emotion polarity.
The judgment criterion is that the polarity difference value of the emotion polarity value and the positive emotion polarity standard value is calculated, and the polarity difference value of the emotion polarity value and the negative emotion polarity standard value is calculated.
For example, emotion polarity values of 0.2, -0.9 and 1.2 are obtained for all nodes, respectively. At this time, the polarity difference value between the three nodes and the positive emotion standard value is respectively 0.8, 1.9 and 0.2, and the polarity difference value between the three nodes and the negative emotion standard value is respectively 1.2, 0.1 and 2.2.
Step S630: and determining the emotion polarities of all the nodes according to the polarity difference value, and determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarities of all the nodes.
Specifically, if the polarity difference value between the positive emotion polarity standard value and the negative emotion polarity standard value is larger than the polarity difference value between the positive emotion polarity standard value and the negative emotion polarity standard value, determining the node as the node with negative emotion polarity, otherwise, if the polarity difference value between the positive emotion polarity standard value and the negative emotion polarity standard value is smaller than the polarity difference value between the positive emotion polarity standard value and the negative emotion polarity standard value, determining the node as the node with positive emotion polarity.
According to the number of nodes with positive emotion polarities and the number of nodes with negative emotion polarities, the emotion polarity analysis result of the object to be reviewed can be determined.
Therefore, by implementing the alternative embodiment, the emotion polarity of the node is determined through the polarity difference value, so that the complexity of determining the emotion polarity is reduced, the determined emotion polarity is more accurate, and the accuracy of the emotion polarity analysis result of the object to be reviewed is improved.
As an alternative embodiment, please refer to fig. 7, fig. 7 shows a schematic flow chart of determining the emotion polarity analysis result of the object to be reviewed. As shown in fig. 7, may include:
Step S710: and respectively counting the number of nodes with positive emotion polarities and the number of nodes with negative emotion polarities to obtain positive emotion statistical results and negative emotion statistical results.
Specifically, the positive emotion statistical result and the negative emotion statistical result are a number, and the number represents the number of nodes with positive emotion polarity and the number of nodes with negative emotion polarity.
For example, there are 7 nodes, where the number of nodes with positive emotion polarity is 3, the number of nodes with negative emotion polarity is 4, and the positive emotion statistics result is 3, and the negative emotion statistics result is 4.
Step S720: and calculating positive emotion polarity duty ratio and negative emotion polarity duty ratio according to the positive emotion statistic result and the negative emotion statistic result.
Specifically, the positive emotion polarity ratio is the ratio of the number of nodes with positive emotion polarity to the total number of nodes, and the negative emotion polarity ratio is the ratio of the number of nodes with negative emotion polarity to the total number of nodes.
For example, there are 7 nodes, wherein the number of nodes with positive emotion polarity is 3, the number of nodes with negative emotion polarity is 4, the positive emotion statistics result is 3, the negative emotion statistics result is 4, based on which the positive emotion polarity is 3/7, and the negative emotion polarity is 4/7.
Step S730: if the positive emotion polarity proportion is larger than the negative emotion polarity proportion, or the positive emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is a positive emotion polarity result.
Specifically, the positive emotion polarity result is a result that most users have positive emotion on the object to be reviewed.
For example, the positive emotion polarity ratio is 5/7, the negative emotion polarity ratio is 2/7, and it is obvious that at this time, the positive emotion polarity ratio is larger than the negative emotion polarity ratio, and then the emotion polarity analysis result of the object to be reviewed is the positive emotion polarity result.
Step S740: if the positive emotion polarity proportion is smaller than the negative emotion polarity proportion, or the negative emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is the negative emotion polarity analysis result.
Specifically, the negative emotion polarity result is a result that most users have negative emotion on the object to be reviewed.
For example, the positive emotion polarity ratio is 3/7, the negative emotion polarity ratio is 4/7, and it is obvious that at this time, the positive emotion polarity ratio is smaller than the negative emotion polarity ratio, and then the emotion polarity analysis result of the object to be reviewed is the negative emotion polarity result.
It can be seen that, by implementing this alternative embodiment, the emotion polarity analysis result of the object to be reviewed can be determined more accurately according to the comparison result between the positive polarity duty ratio and the negative polarity duty ratio.
As an alternative embodiment, it may further include: and determining the user node with the positive emotion polarity, and recommending the object to be commented and/or other objects to be commented similar to the object to be commented to the user corresponding to the user node.
Specifically, the user node with the positive emotion polarity is a user who has a positive emotion tendency for the object to be reviewed, so that the object to be reviewed can be recommended to the user or other objects to be reviewed similar to the object to be reviewed can be recommended to the user.
For example, the user with positive emotion polarity is user node a, and at this time, the user 1 corresponding to user node a may be recommended to the object to be reviewed, i.e. song a, and also the user 1 may be recommended to song B having the same song as song a.
Therefore, by implementing the alternative embodiment, only the user nodes with the positive emotion polarities are recommended, and the recommending efficiency and accuracy are improved.
As an alternative embodiment, please refer to fig. 8, fig. 8 shows a schematic flow chart of determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all nodes at the end of the iteration. As shown in fig. 8, may include:
Step S810: and acquiring preset iteration ending times, and determining emotion polarity analysis results of the object to be reviewed according to the emotion polarity value of the node if the iteration times corresponding to the current iteration reach the preset iteration ending times.
Specifically, the preset iteration end number is a preset numerical value, and when the current iteration number is equal to the preset iteration end number, the emotion polarity analysis result of the object to be reviewed is determined according to the emotion polarity value of the node.
For example, if the preset iteration end number is 200, when the iteration number corresponding to the current iteration reaches 200, determining the emotion polarity analysis result of the object to be evaluated according to the emotion polarity values of all the nodes at the time.
Step S820: determining current iteration emotion polarity values of all nodes corresponding to the current iteration, and determining adjacent iteration emotion polarity values of all nodes in an adjacent iteration process; the adjacent iteration process is an iteration process with an iteration sequence relation with the current iteration.
Specifically, in the iteration process, since the determined seed nodes are different in the process of each iteration, the emotion polarity values of the determined nodes may change when each iteration is finished, the emotion polarity values of the current iteration are the emotion polarity values of all the determined nodes when the current iteration is finished, and the emotion polarity values of the adjacent iteration refer to the emotion polarity values of all the nodes when the last iteration is finished.
For example, there are three nodes whose emotion polarity values are 0.3, 1 and 0.2 at the end of the current iteration, and 0.3, 0.98 and 0.2 at the end of the last iteration.
Step S830: and calculating a polarity update value of the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determining emotion analysis results of the object to be reviewed according to the emotion polarity values of all the nodes if the polarity update value is smaller than or equal to a preset polarity change threshold.
Specifically, the polarity update value is a difference value between the current iteration emotion polarity value and the adjacent iteration emotion polarity value, the preset change threshold is a value for judging whether the change condition of the emotion polarity value of the node tends to be stable, and obviously, if the polarity update value is smaller than the preset change threshold, it is proved that the emotion polarity change condition of the node tends to be stable at the moment, and then the emotion analysis result of the object to be reviewed is determined according to the emotion polarity value of the node.
For example, there are three nodes, when the current iteration is finished, the emotion polarity values of the three nodes are respectively 0.3, 1 and 0.2, and when the previous iteration is finished, the emotion polarity values of the three nodes are respectively 0.3, 0.98 and 0.2, based on the emotion polarity values, the polarity update values are respectively 0, 0.02 and 0, and the preset polarity change threshold value is 0.05, and obviously, the polarity update values of all the nodes are smaller than the preset polarity change threshold value at this time, so that the emotion polarity analysis result of the object to be reviewed is determined according to the emotion polarity values of the nodes of 0.3, 1 and 0.2.
Therefore, the implementation of the alternative embodiment provides two conditions for ending the iteration, which is helpful for more accurately determining the emotion polarity value at the end of the iteration, and further improves the accuracy and efficiency of the emotion polarity analysis result determined later.
According to the embodiment of the application, on one hand, a node for determining the emotion polarity value is selected as a seed node, the emotion polarity value of a first object node with a first action association relation with the seed node is determined by taking the seed node as a starting point, the emotion polarity values of other nodes are determined by utilizing the emotion polarity value of the first object emotion node and the second action association relation, so that the emotion polarity analysis result of an object to be commented is determined, the social network information and a natural language processing technology which can only identify short text information are prevented from being used in the process of determining the emotion polarity analysis result, the accuracy and efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged; on the other hand, the emotion polarity values of all the nodes are obtained according to calculation, so that the complexity of determining the emotion polarity analysis result of the object to be reviewed is reduced, and the efficiency of determining the emotion polarity analysis result of the object to be reviewed is further improved.
Exemplary Medium
Having described the methods of the exemplary embodiments of the present application, next, a description will be given of the media of the exemplary embodiments of the present application.
In some possible embodiments, the aspects of the present application may also be implemented as a medium having program code stored thereon, which when executed by a processor of a device, is configured to implement the steps in the information display method according to the various exemplary embodiments of the present application described in the "exemplary method" section of the present specification.
Specifically, the processor of the device is configured to implement the following steps when executing the program code: determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node with a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value; acquiring a second object node with a second behavior association relation with the first object node, and determining the emotion polarity value of the second object node in the current iteration based on the second behavior association relation and the emotion polarity value of the first object node so as to continue iteration until the iteration is finished; and when the iteration is finished, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity values of all the nodes.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: acquiring a first behavioral emotion polarity value corresponding to the first behavioral association relation, and calculating to obtain an emotion polarity value of a first object node according to the first behavioral emotion polarity value and the emotion polarity value of the seed node; and determining a second behavior emotion polarity value corresponding to the second behavior association relation, and calculating the second behavior emotion polarity value and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: when second behavior association relations are established between the comment nodes and the user nodes respectively, polarity calculation weights and emotion polarity values corresponding to the user nodes are obtained; and calculating the emotion polarity value of the comment node according to the second behavior polarity value corresponding to all the second behavior association relations, the polarity calculation weight and the emotion polarity value respectively corresponding to all the user nodes.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: determining emotion polarity values of all nodes at the end of iteration, and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value; if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, respectively calculating polarity difference values between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value; and determining the emotion polarities of all the nodes according to the polarity difference value, and determining the emotion polarity analysis result of the object to be evaluated according to the emotion polarities of all the nodes.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: respectively counting the number of nodes with positive emotion polarities and the number of nodes with negative emotion polarities to obtain positive emotion statistical results and negative emotion statistical results; according to the positive emotion statistical result and the negative emotion statistical result, calculating to obtain a positive emotion polarity duty ratio and a negative emotion polarity duty ratio; if the positive emotion polarity proportion is larger than the negative emotion polarity proportion, or the positive emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be commented is a positive emotion polarity result; if the positive emotion polarity proportion is smaller than the negative emotion polarity proportion, or the negative emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is the negative emotion polarity analysis result.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: and determining the user node with the positive emotion polarity, and recommending the object to be commented and/or other objects to be commented similar to the object to be commented to the user corresponding to the user node.
In some embodiments of the present application, the processor of the apparatus is further configured to implement the following steps when executing the program code: acquiring preset iteration ending times, and determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of the nodes if the iteration times corresponding to the current iteration reach the preset iteration ending times; or determining the current iteration emotion polarity values of all nodes corresponding to the current iteration, and determining the adjacent iteration emotion polarity values of all nodes in the adjacent iteration process; wherein, the adjacent iterative process is an iterative process with an iterative sequence relation with the current iteration;
and calculating a polarity updating value of the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determining an emotion analysis result of the object to be reviewed according to the emotion polarity values of all nodes if the polarity updating value is smaller than or equal to a preset polarity change threshold value.
It should be noted that: the medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take many forms, including, but not limited to: electromagnetic signals, optical signals, or any suitable combination of the preceding. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Exemplary apparatus
Having described the medium according to the exemplary embodiment of the present application, next, an emotion polarity analysis device according to the exemplary embodiment of the present application will be described with reference to fig. 9.
Referring to fig. 9, fig. 9 is a block diagram illustrating a emotion polarity analysis device according to an exemplary embodiment of the present application. As shown in fig. 9, an emotion polarity analysis device 900 according to an exemplary embodiment of the present application includes: acquisition unit 910, iteration unit 920, and emotion polarity analysis unit 930, wherein:
an obtaining unit 910, configured to determine an emotion polarity value of a seed node corresponding to an object to be reviewed, and obtain a first object node having a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value;
the iteration unit 920 is configured to obtain a second object node having a second behavior association relationship with the first object node, and determine, based on the second behavior association relationship and the emotion polarity value of the first object node, the emotion polarity value of the second object node in the current iteration, so as to continue the iteration until the iteration is ended;
and the emotion polarity analysis unit 930 is used for determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of all nodes when the iteration is finished.
Therefore, the device shown in fig. 9 is implemented, the node for determining the emotion polarity value is selected as the seed node, the emotion polarity value of the first object node with the first action association relation with the seed node is determined by taking the node as the starting point, the emotion polarity values of other nodes are determined by utilizing the emotion polarity value of the first object emotion node and the second action association relation, so that the emotion polarity analysis result of the object to be reviewed is determined, the social network information and the natural language processing technology which can only identify short text information are prevented from being used in the process of determining the emotion polarity analysis result, the accuracy and the efficiency of the determined emotion polarity analysis result are improved, and the application scene for determining the emotion polarity analysis result is enlarged.
In one embodiment, based on the foregoing scheme, the iteration unit 920 determines the emotion polarity value of the second object node in the current iteration based on the second behavior association relationship and the emotion polarity value of the first object node, including:
acquiring a first behavioral emotion polarity value corresponding to the first behavioral association relation, and calculating to obtain an emotion polarity value of a first object node according to the first behavioral emotion polarity value and the emotion polarity value of the seed node;
And determining a second behavior emotion polarity value corresponding to the second behavior association relation, and calculating the second behavior emotion polarity value and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration.
Therefore, according to the implementation of the alternative embodiment, on one hand, the emotion polarity value of the first object node and the emotion polarity value of the second object node are obtained through calculation, the complexity of the emotion polarity analysis result of the object to be reviewed is reduced, the efficiency of determining the emotion polarity analysis result of the object to be reviewed is further improved, on the other hand, the emotion polarity value of the first behavior emotion polarity value, the emotion polarity value of the second behavior emotion polarity value and the emotion polarity value of the seed node are all values with direct relation with emotion tendencies, the accuracy of determining the emotion polarity analysis result of the object to be reviewed is improved, only the emotion polarity of short text information can not be identified, and the use scene of emotion polarity analysis is enlarged.
In one embodiment, based on the foregoing scheme, the iteration unit 920 calculates the emotion polarity value of the second object node and the emotion polarity value of the first object node to obtain the emotion polarity value of the second object node in the current iteration, where the method includes:
When second behavior association relations are established between the comment nodes and the user nodes respectively, polarity calculation weights and emotion polarity values corresponding to the user nodes are obtained;
and calculating the emotion polarity value of the comment node according to the second behavior polarity value corresponding to all the second behavior association relations, the polarity calculation weight and the emotion polarity value respectively corresponding to all the user nodes.
Therefore, when the alternative embodiment is implemented, the polarity calculation weight is added when the emotion polarity value of the comment node is calculated, so that factors influencing the emotion polarity value of the comment node are perfected, and the accuracy of the determined emotion polarity value of the comment node is further improved.
In one embodiment, based on the foregoing scheme, when the iteration unit 920 iterates to end, determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarity value of the node, including:
determining emotion polarity values of all nodes at the end of iteration, and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value;
if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, respectively calculating polarity difference values between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value;
And determining the emotion polarities of all the nodes according to the polarity difference value, and determining the emotion polarity analysis result of the object to be evaluated according to the emotion polarities of all the nodes.
Therefore, by implementing the alternative embodiment, the emotion polarity of the node is determined through the polarity difference value, so that the complexity of determining the emotion polarity is reduced, the determined emotion polarity is more accurate, and the accuracy of the emotion polarity analysis result of the object to be reviewed is improved.
In one embodiment, based on the foregoing scheme, the iteration unit 920 determines, according to the emotion polarities of all the nodes, an emotion polarity analysis result of the object to be reviewed, including:
respectively counting the number of nodes with positive emotion polarities and the number of nodes with negative emotion polarities to obtain positive emotion statistical results and negative emotion statistical results;
according to the positive emotion statistical result and the negative emotion statistical result, calculating to obtain a positive emotion polarity duty ratio and a negative emotion polarity duty ratio;
if the positive emotion polarity proportion is larger than the negative emotion polarity proportion, or the positive emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be commented is a positive emotion polarity result;
If the positive emotion polarity proportion is smaller than the negative emotion polarity proportion, or the negative emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is the negative emotion polarity analysis result.
It can be seen that, by implementing this alternative embodiment, the emotion polarity analysis result of the object to be reviewed can be determined more accurately according to the comparison result between the positive polarity duty ratio and the negative polarity duty ratio.
In one embodiment, based on the foregoing scheme, the iteration unit 920, the method further includes: and determining the user node with the forward emotion, and recommending the object to be reviewed and/or other objects to be reviewed similar to the object to be reviewed to the user corresponding to the user node.
Therefore, by implementing the alternative embodiment, only the user nodes with the positive emotion polarities are recommended, and the recommending efficiency and accuracy are improved.
In one embodiment, based on the foregoing scheme, the emotion polarity analysis unit 930 determines, at the end of the iteration, an emotion polarity analysis result of the object to be reviewed according to emotion polarity values of all nodes, where the emotion polarity analysis result includes:
acquiring preset iteration ending times, and determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of the nodes if the iteration times corresponding to the current iteration reach the preset iteration ending times; or (b)
Determining current iteration emotion polarity values of all nodes corresponding to the current iteration, and determining adjacent iteration emotion polarity values of all nodes in an adjacent iteration process; wherein, the adjacent iterative process is an iterative process with an iterative sequence relation with the current iteration;
and calculating a polarity update value of the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determining emotion analysis results of the object to be reviewed according to the emotion polarity values of all the nodes if the polarity update value is smaller than or equal to a preset polarity change threshold.
Therefore, the implementation of the alternative embodiment provides two conditions for ending the iteration, which is helpful for more accurately determining the emotion polarity value at the end of the iteration, and further improves the accuracy and efficiency of the emotion polarity analysis result determined later.
It should be noted that although several modules or units of emotion polarity analysis device are mentioned in the detailed description above, this division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Exemplary electronic device
Having described the methods, media, and apparatus of exemplary embodiments of the present application, next, an electronic device according to another exemplary embodiment of the present application is described.
Those skilled in the art will appreciate that the various aspects of the present application may be implemented as a system, method, or program product. Accordingly, aspects of the present application may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 1000 according to such an embodiment of the present disclosure is described below with reference to fig. 10. The electronic device 1000 shown in fig. 10 is merely an example and should not be construed as limiting the functionality and scope of use of the disclosed embodiments.
As shown in fig. 10, the electronic device 1000 is embodied in the form of a general purpose computing device. Components of electronic device 1000 may include, but are not limited to: the at least one processing unit 1010, the at least one memory unit 1020, a bus 1030 connecting the various system components (including the memory unit 1020 and the processing unit 1010), and a display unit 1040.
Wherein the storage unit stores program code that is executable by the processing unit 1010 such that the processing unit 1010 performs steps according to various exemplary embodiments of the present disclosure described in the above-described "exemplary methods" section of the present specification.
The memory unit 1020 may include readable media in the form of volatile memory units such as Random Access Memory (RAM) 1021 and/or cache memory unit 1022, and may further include Read Only Memory (ROM) 1023.
Storage unit 1020 may also include a program/usage tool 1024 having a set (at least one) of program modules 1025, such program modules 1025 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which may include the reality of a network environment, or some combination thereof.
Bus 1030 may include a data bus, an address bus, and a control bus.
The electronic device 1000 can also communicate with one or more external devices 1070 (e.g., keyboard, pointing device, bluetooth device, etc.) that can communicate via an input/output (I/O) interface 1050. Also, electronic device 1000 can communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 1060. As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 over the bus 1030. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 1000, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the present disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
While the spirit and principles of this application have been described with reference to several particular embodiments, it is to be understood that this application is not limited to the disclosed particular embodiments nor does it imply that features in the various aspects are not useful in combination, nor are they intended to be in any way useful for the convenience of the description. The application is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (16)
1. A method of emotion polarity analysis, the method comprising:
determining an emotion polarity value of a seed node corresponding to an object to be reviewed, and acquiring a first object node with a first behavioral association relationship with the seed node; the seed node is a node for determining the emotion polarity value;
acquiring a second object node with a second behavior association relation with the first object node, and acquiring a polarity calculation weight and an emotion polarity value respectively corresponding to the first object node;
according to the second behavior polarity values corresponding to all the second behavior association relations, the polarity calculation weights corresponding to all the first object nodes respectively, and the emotion polarity values, emotion polarity values of the second object nodes are calculated, so that an iteration process is completed;
Selecting one or more nodes which are different from the seed nodes determined in the previous iteration process as seed nodes corresponding to the object to be commented in the next iteration when the next iteration starts, so as to execute the next iteration process, and circulating until the iteration ending condition is met;
and when the iteration is finished, respectively calculating polarity differences among the emotion polarity values, positive emotion polarity standard values and negative emotion polarity standard values of all the nodes, and determining emotion polarities of all the nodes according to the polarity differences so as to determine emotion polarity analysis results of the object to be reviewed according to the emotion polarities of all the nodes.
2. The emotion polarity analysis method of claim 1, wherein the obtaining emotion polarity values respectively corresponding to the first object nodes includes:
and acquiring a first behavioral emotion polarity value corresponding to the first behavioral association relation, and calculating to obtain the emotion polarity value of the first object node according to the first behavioral emotion polarity value and the emotion polarity value of the seed node.
3. The emotion polarity analysis method of claim 1, wherein said first object node comprises a user node and said second object node comprises a comment node;
The calculating according to the second behavior polarity values corresponding to all the second behavior association relations, the polarity calculation weights corresponding to all the first object nodes respectively, and the emotion polarity values, to obtain emotion polarity values of the second object nodes includes:
determining a second behavior emotion polarity value corresponding to the second behavior association relation;
when second behavior association relations are established between the evaluation node and the user nodes respectively, polarity calculation weights and emotion polarity values corresponding to the user nodes respectively are obtained;
and calculating to obtain the emotion polarity value of the evaluation node according to the second behavior polarity value corresponding to all the second behavior association relations, the polarity calculation weight corresponding to all the user nodes and the emotion polarity value.
4. A method according to any one of claims 1 to 3, wherein at the end of the iteration, calculating polarity differences between the emotion polarity values and positive emotion polarity standard values and negative emotion polarity standard values of all nodes, respectively, and determining emotion polarities of all nodes according to the polarity differences, so as to determine emotion polarity analysis results of the object to be reviewed according to the emotion polarities of all nodes, includes:
Determining emotion polarity values of all nodes at the end of iteration, and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value;
if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, calculating polarity difference values between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value respectively;
and determining the emotion polarities of all the nodes according to the polarity difference value, and determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarities of all the nodes.
5. The emotion polarity analysis method of claim 4, wherein said determining emotion polarity analysis results of said object to be reviewed based on said emotion polarities of all said nodes comprises:
respectively counting the number of the nodes with positive emotion polarities and the number of the nodes with negative emotion polarities to obtain positive emotion statistical results and negative emotion statistical results;
calculating positive emotion polarity duty ratio and negative emotion polarity duty ratio according to the positive emotion statistical result and the negative emotion statistical result;
If the positive emotion polarity duty ratio is larger than the negative emotion polarity duty ratio, or the positive emotion statistical result is larger than or equal to a polarity number threshold value, determining that the emotion polarity analysis result of the object to be commented is a positive emotion polarity result;
and if the positive emotion polarity proportion is smaller than the negative emotion polarity proportion, or the negative emotion statistical result is larger than or equal to the polarity number threshold, determining that the emotion polarity analysis result of the object to be reviewed is a negative emotion polarity analysis result.
6. The emotion polarity analysis method of claim 5, further comprising:
and determining the user node with the forward emotion polarity, and recommending the object to be reviewed and/or other objects to be reviewed similar to the object to be reviewed to the user corresponding to the user node.
7. The emotion polarity analysis method of claim 1, wherein at the end of the iteration, calculating polarity differences between emotion polarity values and positive emotion polarity standard values and negative emotion polarity standard values of all nodes, respectively, determining emotion polarities of all nodes according to the polarity differences, and determining emotion polarity analysis results of the object to be reviewed according to the emotion polarities of all nodes, includes:
Acquiring preset iteration ending times, and determining emotion polarity analysis results of the object to be reviewed according to emotion polarity values of the nodes if the iteration times corresponding to the current iteration reach the preset iteration ending times; or (b)
Determining current iteration emotion polarity values of all nodes corresponding to the current iteration, and determining adjacent iteration emotion polarity values of all nodes in an adjacent iteration process; wherein the adjacent iteration process is an iteration process having an iteration sequence relation with the current iteration;
and calculating the polarity updating value of the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determining the emotion analysis result of the object to be reviewed according to the emotion polarity values of all nodes if the polarity updating value is smaller than or equal to a preset polarity change threshold value.
8. An emotion polarity analysis device, comprising:
the system comprises an acquisition unit, a first operation unit and a second operation unit, wherein the acquisition unit is used for determining the emotion polarity value of a seed node corresponding to an object to be reviewed and acquiring a first object node with a first behavior association relation with the seed node; the seed node is a node for determining the emotion polarity value;
The iteration unit is used for acquiring a second object node with a second behavior association relation with the first object node and acquiring a polarity calculation weight and an emotion polarity value respectively corresponding to the first object node; according to the second behavior polarity values corresponding to all the second behavior association relations, the polarity calculation weights corresponding to all the first object nodes respectively, and the emotion polarity values, emotion polarity values of the second object nodes are calculated, so that an iteration process is completed; selecting one or more nodes which are different from the seed nodes determined in the previous iteration process as seed nodes corresponding to the object to be commented in the next iteration when the next iteration starts, so as to execute the next iteration process, and circulating until the iteration ending condition is met;
and the emotion polarity analysis unit is used for respectively calculating the emotion polarity values of all nodes and the polarity difference value between the positive emotion polarity standard value and the negative emotion polarity standard value when iteration is finished, and determining the emotion polarities of all the nodes according to the polarity difference value so as to determine the emotion polarity analysis result of the object to be reviewed according to the emotion polarities of all the nodes.
9. The apparatus of claim 8, wherein the obtaining emotion polarity values respectively corresponding to the first object nodes comprises:
the first calculating unit is used for obtaining a first behavioral emotion polarity value corresponding to the first behavioral association relation, and calculating to obtain the emotion polarity value of the first object node according to the first behavioral emotion polarity value and the emotion polarity value of the seed node.
10. The apparatus of claim 8, wherein the first object node comprises a user node and the second object node comprises a comment node;
the method includes the steps that according to second behavior polarity values corresponding to all second behavior association relations, the polarity calculation weights corresponding to all first object nodes respectively, and the emotion polarity values, emotion polarity values of the second object nodes are calculated, and the device includes:
the second computing unit is used for determining a second behavior emotion polarity value corresponding to the second behavior association relation;
the association unit is used for acquiring polarity calculation weights and emotion polarity values corresponding to the user nodes when second behavior association relations are established between the evaluation nodes and the user nodes respectively;
And a third calculation unit, configured to calculate, according to second behavior polarity values corresponding to all the second behavior association relationships, the polarity calculation weights corresponding to all the user nodes, and the emotion polarity values, an emotion polarity value of the evaluation node.
11. The apparatus according to any one of claims 8 to 10, wherein at the end of the iteration, polarity differences between emotion polarity values and positive emotion polarity standard values and negative emotion polarity standard values of all nodes are calculated, respectively, emotion polarities of all the nodes are determined according to the polarity differences, so as to determine emotion polarity analysis results of the object to be reviewed according to the emotion polarities of all the nodes, the apparatus comprising:
the first determining unit is used for determining the emotion polarity values of all nodes at the end of iteration and obtaining a positive emotion polarity standard value and a negative emotion polarity standard value;
a fourth calculation unit, configured to calculate, if the emotion polarity value is inconsistent with the positive emotion polarity standard value and the negative emotion polarity standard value, a polarity difference value between the emotion polarity value and the positive emotion polarity standard value and between the emotion polarity value and the negative emotion polarity standard value, respectively;
And the second determining unit is used for determining the emotion polarities of all the nodes according to the polarity difference value and determining emotion polarity analysis results of the objects to be reviewed according to the emotion polarities of all the nodes.
12. The apparatus of claim 11, wherein the determining the emotion polarity analysis result of the object to be reviewed according to the emotion polarities of all the nodes comprises:
the statistics unit is used for respectively counting the number of the nodes with positive emotion polarities and the number of the nodes with negative emotion polarities so as to obtain positive emotion statistics results and negative emotion statistics results;
a fifth calculation unit, configured to calculate, according to the positive emotion statistics result and the negative emotion statistics result, a positive emotion polarity duty ratio and a negative emotion polarity duty ratio;
the third determining unit is used for determining that the emotion polarity analysis result of the object to be reviewed is a positive emotion polarity result if the positive emotion polarity duty ratio is greater than the negative emotion polarity duty ratio or the positive emotion statistical result is greater than or equal to a polarity number threshold;
And the fourth determining unit is used for determining that the emotion polarity analysis result of the object to be reviewed is a negative emotion polarity analysis result if the positive emotion polarity proportion is smaller than the negative emotion polarity proportion or the negative emotion statistical result is larger than or equal to the polarity number threshold.
13. The apparatus of claim 12, wherein the apparatus further comprises:
and the recommending unit is used for determining the user node with the forward emotion polarity and recommending the object to be reviewed and/or other objects to be reviewed similar to the object to be reviewed to the user corresponding to the user node.
14. The apparatus of claim 8, wherein at the end of the iteration, polarity differences between the emotion polarity values and positive emotion polarity standard values and negative emotion polarity standard values of all nodes are calculated, emotion polarities of all the nodes are determined according to the polarity differences, and emotion polarity analysis results of the object to be reviewed are determined according to the emotion polarities of all the nodes, the apparatus comprising:
a fifth determining unit, configured to obtain a preset iteration end number, and determine an emotion polarity analysis result of the object to be reviewed according to the emotion polarity value of the node if the iteration number corresponding to the current iteration reaches the preset iteration end number; or (b)
A sixth determining unit, configured to determine current iteration emotion polarity values of all nodes corresponding to the current iteration, and determine adjacent iteration emotion polarity values of all the nodes in an adjacent iteration process; wherein the adjacent iteration process is an iteration process having an iteration sequence relation with the current iteration;
and a seventh determining unit, configured to calculate a polarity update value between the current iteration emotion polarity value and the adjacent iteration emotion polarity value, and determine an emotion analysis result of the object to be reviewed according to emotion polarity values of all nodes if the polarity update value is less than or equal to a preset polarity change threshold.
15. An electronic device, comprising:
a processor;
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the emotion polarity analysis method of any one of claims 1-7 via execution of the executable instructions.
16. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the emotion polarity analysis method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110868892.7A CN113688202B (en) | 2021-07-30 | 2021-07-30 | Emotion polarity analysis method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110868892.7A CN113688202B (en) | 2021-07-30 | 2021-07-30 | Emotion polarity analysis method and device, electronic equipment and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113688202A CN113688202A (en) | 2021-11-23 |
CN113688202B true CN113688202B (en) | 2024-03-15 |
Family
ID=78578340
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110868892.7A Active CN113688202B (en) | 2021-07-30 | 2021-07-30 | Emotion polarity analysis method and device, electronic equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113688202B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114286155B (en) * | 2021-12-07 | 2024-07-19 | 咪咕音乐有限公司 | Bullet screen-based picture element modification method, bullet screen-based picture element modification device, bullet screen-based picture element modification equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105354305A (en) * | 2015-11-05 | 2016-02-24 | 北京邮电大学 | Online-rumor identification method and apparatus |
JP2016162357A (en) * | 2015-03-04 | 2016-09-05 | Kddi株式会社 | Analysis device and program of user's emotion to product |
CN106780073A (en) * | 2017-01-11 | 2017-05-31 | 中南大学 | A kind of community network maximizing influence start node choosing method for considering user behavior and emotion |
CN108256098A (en) * | 2018-01-30 | 2018-07-06 | ***股份有限公司 | A kind of method and device of determining user comment Sentiment orientation |
CN108460009A (en) * | 2017-12-14 | 2018-08-28 | 中山大学 | The attention mechanism Recognition with Recurrent Neural Network text emotion analytic approach of embedded sentiment dictionary |
CN109766477A (en) * | 2018-12-26 | 2019-05-17 | 杭州铭智云教育科技有限公司 | A method of obtaining positive target user |
CN110070410A (en) * | 2019-03-07 | 2019-07-30 | 特斯联(北京)科技有限公司 | A kind of population social activity analysis method and system based on big data |
CN110489553A (en) * | 2019-07-26 | 2019-11-22 | 湖南大学 | A kind of sensibility classification method based on Multi-source Information Fusion |
CN112364170A (en) * | 2021-01-13 | 2021-02-12 | 北京智慧星光信息技术有限公司 | Data emotion analysis method and device, electronic equipment and medium |
CN113032684A (en) * | 2019-12-05 | 2021-06-25 | 天津科技大学 | Food safety network public opinion propagation evolution modeling method based on complex network |
CN113157899A (en) * | 2021-05-27 | 2021-07-23 | 东莞心启航联贸网络科技有限公司 | Big data portrait analysis method, server and readable storage medium |
-
2021
- 2021-07-30 CN CN202110868892.7A patent/CN113688202B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016162357A (en) * | 2015-03-04 | 2016-09-05 | Kddi株式会社 | Analysis device and program of user's emotion to product |
CN105354305A (en) * | 2015-11-05 | 2016-02-24 | 北京邮电大学 | Online-rumor identification method and apparatus |
CN106780073A (en) * | 2017-01-11 | 2017-05-31 | 中南大学 | A kind of community network maximizing influence start node choosing method for considering user behavior and emotion |
CN108460009A (en) * | 2017-12-14 | 2018-08-28 | 中山大学 | The attention mechanism Recognition with Recurrent Neural Network text emotion analytic approach of embedded sentiment dictionary |
CN108256098A (en) * | 2018-01-30 | 2018-07-06 | ***股份有限公司 | A kind of method and device of determining user comment Sentiment orientation |
CN109766477A (en) * | 2018-12-26 | 2019-05-17 | 杭州铭智云教育科技有限公司 | A method of obtaining positive target user |
CN110070410A (en) * | 2019-03-07 | 2019-07-30 | 特斯联(北京)科技有限公司 | A kind of population social activity analysis method and system based on big data |
CN110489553A (en) * | 2019-07-26 | 2019-11-22 | 湖南大学 | A kind of sensibility classification method based on Multi-source Information Fusion |
CN113032684A (en) * | 2019-12-05 | 2021-06-25 | 天津科技大学 | Food safety network public opinion propagation evolution modeling method based on complex network |
CN112364170A (en) * | 2021-01-13 | 2021-02-12 | 北京智慧星光信息技术有限公司 | Data emotion analysis method and device, electronic equipment and medium |
CN113157899A (en) * | 2021-05-27 | 2021-07-23 | 东莞心启航联贸网络科技有限公司 | Big data portrait analysis method, server and readable storage medium |
Non-Patent Citations (3)
Title |
---|
Chenhao Tan.et al.User-level sentiment analysis incorporating social networks.KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining.2011,第1397–1405页. * |
融合用户情感评分的节点专业影响力分析;王仁武等;现代情报;第54-61页 * |
面向微博的情感影响最大化模型;欧高炎等;计算机科学与探索;第769-778页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113688202A (en) | 2021-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109360012B (en) | Advertisement delivery channel selection method and device, storage medium and electronic equipment | |
JP6892484B2 (en) | Method of generating object detection frame and its device, equipment, storage medium and vehicle | |
CN108304324B (en) | Test case generation method, device, equipment and storage medium | |
CN110968985B (en) | Method and device for determining integrated circuit repair algorithm, storage medium and electronic equipment | |
CN109461023B (en) | Loss user retrieval method and device, electronic equipment and storage medium | |
CN105574098A (en) | Knowledge graph generation method and device and entity comparing method and device | |
CN111127051B (en) | Multi-channel dynamic attribution method, device, server and storage medium | |
CN109272348B (en) | Method and device for determining number of active users, storage medium and electronic equipment | |
CN110833696A (en) | Player ranking method and device, storage medium and electronic equipment | |
CN111079944B (en) | Transfer learning model interpretation realization method and device, electronic equipment and storage medium | |
CN111291936B (en) | Product life cycle prediction model generation method and device and electronic equipment | |
CN110704727A (en) | Information pushing method and device and computer equipment | |
CN113688202B (en) | Emotion polarity analysis method and device, electronic equipment and computer storage medium | |
CN110674397B (en) | Method, device, equipment and readable medium for training age point prediction model | |
CN113822693A (en) | Method, device, equipment and storage medium for generating user purchasing power evaluation value | |
CN117573507A (en) | Test case generation method and device, electronic equipment and storage medium | |
US20230196245A1 (en) | Method and apparatus for predicting risk, electronic device, computer readable storage medium | |
CN109857816B (en) | Test sample selection method and device, storage medium and electronic equipment | |
CN109710523B (en) | Visual draft test case generation method and device, storage medium and electronic equipment | |
CN116541069A (en) | Key function evaluation method, device, electronic equipment, medium and program product | |
CN116563007A (en) | Credit risk prediction method, electronic equipment and readable storage medium | |
CN116304236A (en) | User portrait generation method and device, electronic equipment and storage medium | |
CN116257758A (en) | Model training method, crowd expanding method, medium, device and computing equipment | |
CN115204931A (en) | User service policy determination method and device and electronic equipment | |
CN114035729A (en) | Electronic voting method and device and terminal equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |