CN109885656A - Microblogging forwarding prediction technique and device based on quantization temperature - Google Patents
Microblogging forwarding prediction technique and device based on quantization temperature Download PDFInfo
- Publication number
- CN109885656A CN109885656A CN201910119276.4A CN201910119276A CN109885656A CN 109885656 A CN109885656 A CN 109885656A CN 201910119276 A CN201910119276 A CN 201910119276A CN 109885656 A CN109885656 A CN 109885656A
- Authority
- CN
- China
- Prior art keywords
- topic
- microblog
- temperature
- microblogging
- content
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of microblogging forwarding prediction techniques and device based on quantization temperature, the described method includes: it is assumed that the daily total transfer amount of microblog is constant, the temperature that the same day all topics read the ratio-dependent of the total amount topic is accounted for according to the amount of reading on the day of each topic daily, and the temperature based on the topic is ranked up microblog topic, obtains real-time microblog hot topic table；Content of microblog is compared with the top n microblog topic in microblog hot topic table, the temperature of content of microblog Yu the microblog topic is determined according to the correlation of content of microblog and topic content, and the temperature by content of microblog relative to each topic adds up, and obtains final microblogging temperature；Microblogging forwarding is predicted according to microblogging temperature and essential characteristic.
Description
Technical field
The present invention relates to social networks big data analysis field more particularly to a kind of microblogging forwarding based on quantization temperature are pre-
Survey method and device.
Background technique
Relative to traditional media such as newspaper, broadcast, TVs, the main feature of microblogging is that message spread speed is fast and range
Greatly, popular microblogging short several hours since news release can diffuse to several ten million or even more than one hundred million users.Why is microblogging
It so can broadly spread news fastly, main cause is its virus-type circulation way: the recipient of message can forward him to be seen
The microblogging arrived becomes publisher from message recipient, and numerous beans vermicelli can see that the microblogging that he forwards, these beans vermicelli may be used also
To be forwarded again, the circulation way of this virus-type makes Twitter message be able to explosion type diffusion in the twinkling of an eye.Although in microblogging
There is also other routes of transmission such as "@", platform push, but forward the master for being undoubtedly and the Twitter message short time being promoted to propagate on a large scale
Want mode.Research microblogging forwarding behavior all has information propagation, information popularization, focus incident prediction, public sentiment Situation Awareness etc.
There are important theory and realistic meaning.
Summary of the invention
The embodiment of the present invention provides a kind of microblogging forwarding prediction technique and device based on quantization temperature, existing to solve
The above problem in technology.
The embodiment of the present invention provides a kind of microblogging forwarding prediction technique based on quantization temperature, comprising:
It is assumed that the daily total transfer amount of microblog is constant, daily according to the amount of reading on the day of each topic
Account for the temperature that the same day all topics read the ratio-dependent of the total amounts topic, and the temperature based on the topic to microblog topic into
Row sequence, obtains real-time microblog hot topic table；
Content of microblog is compared with the top n microblog topic in microblog hot topic table, according to content of microblog and words
The correlation of topic content determines the temperature of content of microblog Yu the microblog topic, and the temperature by content of microblog relative to each topic
It adds up, obtains final microblogging temperature；
Microblogging forwarding is predicted according to microblogging temperature and essential characteristic.
Preferably, all topics read the summation for reading number that total amount is M topic before same day microblog topic ranking.
Preferably, it is assumed that the daily total transfer amount of microblog is constant, daily according to each topic same day
Amount of reading account for the temperature that the same day all topics read the ratio-dependent of the total amounts topic, and the temperature based on the topic is to micro-
Rich topic is ranked up, and is obtained real-time microblog hot topic table and is specifically included:
The reading number of M most popular daily topic of continuous acquisition, increased reading number, is denoted as on the day of calculating each topic
ReadTopic [i, j] indicates the reading number in i-th day topic j；
Each topic is ranked up according to amount of reading；
The same day most hot M topic, which is calculated, according to formula 1 reads total amount:
Wherein, Read [i] is that i-th day topic reads total amount；
The temperature of i-th day topic j is calculated according to formula 2:
It is sorted to each topic according to temperature according to the calculated result of formula 2, obtains real-time microblog hot topic table.
Preferably, content of microblog is compared with the top n microblog topic in microblog hot topic table, according in microblogging
Hold the temperature that content of microblog Yu the microblog topic are determined with the correlation of topic content, and by content of microblog relative to each topic
Temperature add up, the temperature for obtaining final microblogging specifically includes:
When acquiring microblog topic, Q microblogging under microblog topic is acquired, Chinese word segmentation is carried out to these microbloggings and is removed
Stop words calculates its TF-IDF value to remaining each word, using word in the top as the keyword closely related with the topic,
Expansion-word set of the K word as the topic before taking；
For any microblogging w, if in w completely include topic, it is determined that the two similarity be 1, otherwise to w into
Row participle constructs term vector Vw after removing stop words, while constructing term vector Vh according to topic and expansion-word set, calculates more than the two
String angle and as the similarity of w and microblog topic h；Calculate the product of the temperature of similarity and microblog topic h, and by its
Temperature as w relative to topic h；
Temperature by microblogging relative to ranking top n hot topic adds up, and obtains the temperature of final microblogging.
Preferably, the essential characteristic specifically includes: user characteristics, social characteristics, temporal characteristics and content characteristic.
The embodiment of the present invention also provides a kind of microblogging forwarding prediction meanss based on quantization temperature, comprising: memory, processing
Device and it is stored in the computer program that can be run on the memory and on the processor, the computer program is described
The step of above method is realized when processor executes.
Using the embodiment of the present invention, prediction effect can be effectively improved, wherein precision improves 2%-3%, and recall rate improves
2%-7%.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the schematic diagram of the communication process of Twitter message in the embodiment of the present invention；
Fig. 2 is the schematic diagram in the embodiment of the present invention between microblogging temperature and forwarding probability；
Fig. 3 be in the embodiment of the present invention microblogging temperature relative to the cumulative distribution function CDF curve for forwarding and ignoring
Figure；
Fig. 4 is the process flow diagram of the microblogging forwarding prediction technique in the embodiment of the present invention based on quantization temperature.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
The research object of the embodiment of the present invention is microblog users and message, indicates microblog users set with U, W indicates microblogging
Massage set, it is assumed that the forwarding behavior that microblogging only passes through user is propagated.The communication process of Twitter message is described in Fig. 1:
Known users u0∈ U has issued a microblogging w ∈ W, and the propagation path of the microblogging is P (u after repeatedly forwarding0,u1,u2…ul,
um, un), u1~umFor the user for forwarding w on propagation path.Solid arrow indicates that forwarding behavior, dotted arrow indicate to close in Fig. 1
Note relationship, such as user umIt is directed toward unSolid arrow indicate umIt forwarded ulMicroblogging w, user unIt is directed toward umDotted arrow un
U is paid close attention tom, such unIt can see umAll microbloggings of publication and forwarding.From u0To umAll forwarding behaviors on propagation path,
The information such as time, user property, content of microblog can be got by API and crawler.What the embodiment of the present invention to be solved asks
It is entitled: to work as unSee umWhen the microblogging w of forwarding, if can forward.
Microblogging is typical social networks, and the number of information forwarding meets power law distribution, and only a few hot topic microblogging is multiple
Forwarding, and the number that most microbloggings are forwarded is seldom, user is more likely to the microblogging of forwarding " hot topic ".It is micro- for " hot topic "
Rich also there are two types of different understandings: one is come what is evaluated, be meant that the content of microblogging is instantly from the content angle of microblogging
Popular.Another is evaluated from the angle of microblogging propagation, and the very extensive microblogging of which propagation is referred mainly to.The latter is only
It can be propagated in microblogging and complete or be basically completed Shi Caineng to know whether as popular microblogging.And the former can be when just issuing just
Can analyze whether it is popular.The popular microblogging of the embodiment of the present invention refers to the first definition.
Microblogging temperature refers to that user to the degree of concern of the content of microblog, reflects the pass of microblogging Yu current hot spot of public opinions
System, but " hot topic " is a subjective impression, lacks unified, authoritative definition method.Microblog does not have itself yet
Correlation is for the explanation of microblogging " temperature ", and by the in-depth analysis to popular microblogging and microblog, the embodiment of the present invention is found
Two facts:
(1) popular microblogging is mostly related with current hot topic semantically；
(2) microblogging has specific mark to topic, it is often more important that microblogging has real-time system to the amount of reading of each topic
Ranking is counted, and can readily be collected.
Based on the two phenomenons, the embodiment of the present invention proposes a kind of thinking of objective description microblogging temperature, talks with first
The temperature of topic is quantified, and the temperature of content of microblog is then defined according to the similarity of microblogging and topic.
Specifically, the present invention implements to propose a kind of hot value of the quantization method of microblogging temperature to calculate any microblogging,
It predicts whether the microblogging can be forwarded based on temperature combination other feature, implementation of the present invention is finally demonstrated in real data set
The validity of the example technical solution.The main contents of the embodiment of the present invention are as follows:
(1) the temperature quantization method of the microblog topic based on temperature competition is proposed.Turn it is assumed that microblog is total daily
Hair amount is constant, so that the amount of reading on the day of being the topic for the temperature of topic accounts for the ratio that the same day all topics read total amount, mentions
Relevant calculation method out.
(2) the temperature computational algorithm for any Twitter message is proposed.The content of microblogging and each topic are compared
Compared with measuring the temperature of microblogging according to the correlation of content of microblog and topic content and the temperature of topic.
(3) the forwarding prediction technique based on the quantization of microblogging temperature is proposed.Analytic explanation microblogging temperature is prediction microblogging
One validity feature of forwarding, and on forefathers' Research foundation, by user characteristics, social characteristics, temporal characteristics, content characteristic etc.
Essential characteristic combination microblogging temperature feature is predicted to complete forwarding.
(4) selection and parameter setting of sorting algorithm in prediction technique are analyzed.
The above description is only an overview of the technical scheme of the present invention, in order to more clearly understand technology hand of the invention
Section cooperates attached drawing to be illustrated below, and specific process flow is as shown in Figure 4.
One, the quantization method of topic temperature
A topic is identified with # topic name # in microblogging.Microblog topic refers to that user discusses on microblogging, makes a speech
Theme is the abstract of the event of users' concern and is summarized.Temperature about topic does not have authoritative definition method at present yet,
But it can be by checking hot topic channel real-time 1 hour and the ranking list of 24 hours topics, according to reading in microblog
Amount is to sort.
This makes it possible to obtain microblog hot topic and its read quantity.It should be noted that directly being adopted by the page
The reading number collected is the accumulative reading number of the topic, rather than reading number when carrying out prediction task.Some topics by
It discusses for a long time, be not popular topic instantly although there are many accumulative reading number.In response to this, we
Only reading quantity Appreciation gist as its temperature of the statistics topic within past 24 hours.Therefore, it is necessary to daily continuous collectings
The accumulative reading number of associated topic could obtain topic and go over 24 hours newly-increased reading numbers.
In view of containing much information on microblogging, topic relatively disperses, we acquire before ranking 1000 topic and reading number daily.
Since preceding 1000 topics are dynamic changes, the topic of top1000 is newly entered for second day and later, we also hold
Continuous acquisition.Simultaneously for the topic for falling top1000 out, we are also acquired, until continuous 10 days all except top1000.
By lasting acquisition and calculating, we have just obtained that most hot topic is currently discussed on microblogging and its have read number.
Two quantizating index have now been attained, topic reads the ranking of number and reads the absolute value of number, but the two indexs
It cannot be by it directly as the index of the temperature of evaluation topic.This is primarily due to the purpose studied herein forwarding prediction, we
The relationship of topic temperature and microblogging forwarding need to further be studied.Pass through the reading of microblog hot topic daily in continuous acquisition one week
Amount finds that the topic amount of reading difference of identical ranking in not same date is larger, as first day and second day are number two topic
Amount of reading differs by about one time, this explanation simply cannot read number ranking using topic for the assessment of topic temperature to measure.Separately
Outside, it has been found that total amount of reading difference is larger within first day and second day, this two days forwarding quantity but changes less.Although hot
Door topic is read the sum of number and is changed greatly, but the total transfer amount of microblogging but fluctuates less, illustrates that amount of reading can not be brought greatly
More forwarding behaviors, it is also unreasonable that topic temperature is measured with the absolute amount of reading of topic.
In addition, the embodiment of the present invention also analyzes the total transfer amount situation of change of microblog, microblog is had found that while
Upper have a different hot topics daily, but the total forwarding quantity of user really fluctuate less, this may be because of all users
Using the total duration of microblogging relatively fixed daily, although daily topic is different, the total amount of forwarding is basically unchanged.Based on this
There is the phenomenon that competition user forwards behavior in a premise, each topic.Therefore, for forwarding prediction, with the reading of topic
It is more reasonable to measure its temperature that several Zhan always reads the ratio of number.
Based on above-mentioned analysis, the embodiment of the present invention proposes a kind of based on the microblog topic temperature amount for paying close attention to power competition between topic
Change method.It is assumed that the daily total transfer amount of microblog is constant, the temperature of topic accounts for same day institute for the amount of reading on the day of the topic
There is topic to read the ratio of total amount.Process to simplify the calculation, approximatively with the sum of amount of reading of 1000 topics before same day ranking
Indicate total topic amount of reading.Under microblog topic temperature quantization method:
1, the reading number of 1000 most popular daily topics of continuous acquisition, increased reading on the day of calculating each topic
Number, is denoted as ReadTopic [i, j], indicates the reading number in i-th day topic j；
2, each topic is ranked up according to amount of reading；
3, the same day most hot 1000 topics are calculated and read total amount,Read [i] is i-th day
Topic reads total amount；
4, i-th day topic j, temperature are as follows:
5, it sorts to each topic according to temperature；
The embodiment of the present invention according to the hot topic of the lasting acquisition Sina weibo of above-mentioned steps and its reads number daily, just
Real-time microblog hot topic table is obtained.
Two, microblogging temperature quantization algorithm
The embodiment of the present invention carries out quantitative evaluation based on temperature of the topic temperature to any microblogging.Basic ideas are by microblogging
Content be compared with each topic, it is micro- to measure according to content of microblog and the correlation of topic content and the temperature of topic
Rich temperature.The semantic extension problem that matter of utmost importance is topic is faced among these.Being generally in the form of for the topic of microblogging is one short
Language is the summary to related content and is abstracted, and cannot only be understood up from the literal of topic.This intermediate main cause is words
Topic is limited to length, is abstracted and has been summarized to related content, therefore, to analyze the correlation of content of microblog with topic, I
The semanteme of topic should be extended first.Specific method is that (there is and the topic each topic in microblogging under acquisition topic
Related microblogging list) 100 microbloggings, these microbloggings are carried out Chinese word segmentation [note] and to remove stop words, to it is remaining respectively
Word calculates its TF-IDF value, and word in the top is considered as the keyword closely related with the topic, and k word, which is used as, before taking is somebody's turn to do
The expansion-word set of topic is denoted as T [i, j].
It is all for topic it is important to note that since the semantic extension of topic is not more big changes usually
Semantic extension work only needs to carry out when acquiring topic once, does not need to compute repeatedly daily.
Further work is the correlation for calculating content of microblog and each topic, is a successive value on [0,1].0 generation
Table is completely uncorrelated, 1 represent it is perfectly correlated.Herein using will be based on the cosine-algorithm of space vector.For any one
Microblogging w, we calculate the similarity of itself and topic h.Firstly, the two similarity is 1 if in w completely including topic.
Otherwise w is segmented, constructs term vector Vw after removing stop words, while term vector Vh is constructed according to topic and expansion-word set,
The two cosine angle is calculated as w and h similarity.The product of similarity and topic h temperature is temperature of the w relative to topic h.
Since a microblogging is possible to related to multiple topics, need to carry out 100 hot topics before microblogging and ranking
Compare, is the final temperature of microblogging after the temperature relative to each topic is cumulative.Heat_w, specific algorithm are as shown in table 1:
Table 1
Three, prediction technique is forwarded
After above-mentioned calculating, a quantized value about content of microblog temperature is obtained, this is an opposite numerical value,
It has reacted compared with other microbloggings that the same period propagates, the attraction of the content of this microblogging to user.This value and its turned
There is which type of relationship on earth in the probability of hair? we are to it into quantitative analysis: to forwarding sample data obtained above
With the temperature for ignoring sample data and calculating wherein every microblogging, then analyzes microblogging temperature and forward the relationship between probability, such as
Shown in Fig. 2.From figure 2 it can be seen that the bigger microblogging hot value the higher on the whole, the probability that it is forwarded by user is just
It is bigger.When temperature is 0, illustrate that the microblogging is uncorrelated to current hot spot of public opinions, when still there is certain forwarding probability, this is because
The key factor that microblogging temperature is only forwarding, rather than all.The also factor of some other influences user forwarding, such as with
Family relationship, user force etc. can promote microblogging to be forwarded when these factors are more abundant temperature is 0.This explanation is micro-
There are positive correlations between rich temperature and forwarding probability.
Further, research microblogging temperature is the validity feature that a differentiation forwards/ignores, and the embodiment of the present invention is drawn
Microblogging temperature is gone out relative to cumulative distribution function CDF (the Cumulative Distribution for forwarding and ignoring
Function) curve graph.It can be seen that whether microblogging temperature can effectively be distinguished by the form of the two to forward and ignore dynamic
Make.Farther out from the curve distance that can be forwarded in most of microblogging temperature section and ignore in Fig. 3, this illustrates that microblogging temperature can be with
It is effective to distinguish forwarding behavior and ignore movement.
It is to predict a validity feature of microblogging forwarding by above analytic explanation microblogging temperature.But microblogging forwards
Not only related with microblogging temperature, a lot of other factors can also promote user to forward microblogging, have many scholars in this side
Face has carried out many fruitful research work, proposes many effective predicted characteristics, such as user force, when forwarding
Between, relationship etc. between user, these features can substantially be divided into: user characteristics, social characteristics, temporal characteristics and content characteristic are several
Class, see Table 1 for details.
Table 1
These these features are called essential characteristic (Basic Features) by present example, in conjunction with microblogging temperature and base
Eigen is predicted to be forwarded.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of microblogging based on quantization temperature forwards prediction technique characterized by comprising
It is assumed that the daily total transfer amount of microblog is constant, is accounted for work as according to the amount of reading on the day of each topic daily
Its all topic reads the temperature of the ratio-dependent of the total amount topic, and the temperature based on the topic arranges microblog topic
Sequence obtains real-time microblog hot topic table；
Content of microblog is compared with the top n microblog topic in microblog hot topic table, according in content of microblog and topic
The correlation of appearance determines the temperature of content of microblog Yu the microblog topic, and the temperature by content of microblog relative to each topic carries out
It is cumulative, obtain final microblogging temperature；
Microblogging forwarding is predicted according to microblogging temperature and essential characteristic.
2. the method as described in claim 1, which is characterized in that it is M before same day microblog topic ranking that all topics, which read total amount,
The summation of the reading number of a topic.
3. method according to claim 2, which is characterized in that it is assumed that the microblog constant situation of total transfer amount daily
Under, the temperature that the same day all topics read the ratio-dependent of the total amount topic is accounted for according to the amount of reading on the day of each topic daily,
And the temperature based on the topic is ranked up microblog topic, obtains real-time microblog hot topic table and specifically includes:
The reading number of M most popular daily topic of continuous acquisition, increased reading number, is denoted as on the day of calculating each topic
ReadTopic [i, j] indicates the reading number in i-th day topic j；
Each topic is ranked up according to amount of reading；
The same day most hot M topic, which is calculated, according to formula 1 reads total amount:
Wherein, Read [i] is that i-th day topic reads total amount；
The temperature of i-th day topic j is calculated according to formula 2:
It is sorted to each topic according to temperature according to the calculated result of formula 2, obtains real-time microblog hot topic table.
4. the method as described in claim 1, which is characterized in that content of microblog and the top n in microblog hot topic table is micro-
Rich topic is compared, and the temperature of content of microblog Yu the microblog topic is determined according to the correlation of content of microblog and topic content,
And the temperature by content of microblog relative to each topic adds up, the temperature for obtaining final microblogging specifically includes:
When acquiring microblog topic, Q microblogging under microblog topic is acquired, Chinese word segmentation is carried out to these microbloggings and is removed deactivated
Word calculates its TF-IDF value to remaining each word, using word in the top as the keyword closely related with the topic, before taking
Expansion-word set of the K word as the topic；
For any microblogging w, if in w completely including topic, it is determined that the two similarity is 1, is otherwise divided w
Word constructs term vector Vw after removing stop words, while constructing term vector Vh according to topic and expansion-word set, calculates the two cosine folder
Angle and as the similarity of w and microblog topic h；The product of calculating similarity and the temperature of microblog topic h, and as
Temperature of the w relative to topic h；
Temperature by microblogging relative to ranking top n hot topic adds up, and obtains the temperature of final microblogging.
5. the method as described in claim 1, which is characterized in that the essential characteristic specifically includes: user characteristics, social spy
Sign, temporal characteristics and content characteristic.
6. a kind of microblogging based on quantization temperature forwards prediction meanss characterized by comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the computer program are held by the processor
It realizes when row such as the step of any one of claims 1 to 5 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910119276.4A CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910119276.4A CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109885656A true CN109885656A (en) | 2019-06-14 |
| CN109885656B CN109885656B (en) | 2021-06-29 |
Family
ID=66928179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910119276.4A Active CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885656B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222909A (en) * | 2019-06-20 | 2019-09-10 | 郑州工程技术学院 | A kind of dissemination of news force prediction method |
| CN110263254A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Event stage division, device, equipment and medium |
| CN110472013A (en) * | 2019-08-06 | 2019-11-19 | 湖南蚁坊软件股份有限公司 | A kind of hot topic update method, device and computer storage medium |
| CN110598151A (en) * | 2019-09-09 | 2019-12-20 | 河南牧业经济学院 | Method and system for judging news spreading effect |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
| CN103853711A (en) * | 2012-11-28 | 2014-06-11 | ***通信集团广西有限公司 | Text information processing method and device |
| CN104933622A (en) * | 2015-03-12 | 2015-09-23 | 中国科学院计算技术研究所 | Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme |
| CN106600071A (en) * | 2016-12-20 | 2017-04-26 | 西南石油大学 | Topic-based microblog forwarding prediction method and system |
| CN107122481A (en) * | 2017-05-04 | 2017-09-01 | 成都华栖云科技有限公司 | News temperature real-time online Forecasting Methodology |
| CN107798027A (en) * | 2016-09-06 | 2018-03-13 | 腾讯科技（深圳）有限公司 | A kind of heatrate Forecasting Methodology, information recommendation method and device |
-
2019
- 2019-02-18 CN CN201910119276.4A patent/CN109885656B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853711A (en) * | 2012-11-28 | 2014-06-11 | ***通信集团广西有限公司 | Text information processing method and device |
| CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
| CN104933622A (en) * | 2015-03-12 | 2015-09-23 | 中国科学院计算技术研究所 | Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme |
| CN107798027A (en) * | 2016-09-06 | 2018-03-13 | 腾讯科技（深圳）有限公司 | A kind of heatrate Forecasting Methodology, information recommendation method and device |
| CN106600071A (en) * | 2016-12-20 | 2017-04-26 | 西南石油大学 | Topic-based microblog forwarding prediction method and system |
| CN107122481A (en) * | 2017-05-04 | 2017-09-01 | 成都华栖云科技有限公司 | News temperature real-time online Forecasting Methodology |
Non-Patent Citations (3)
| Title |
|---|
| SHA YUAN 等: "Realtime Online Hot Topics Prediction in Sina Weibo for News Earlier Report", 《2017 IEEE 31ST INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS》 * |
| 聂恩伦 等: "基于Ｋ近邻的新话题热度预测算法", 《计算机科学》 * |
| 陈江 等: "融合热点话题的微博转发预测研究", 《中文信息学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222909A (en) * | 2019-06-20 | 2019-09-10 | 郑州工程技术学院 | A kind of dissemination of news force prediction method |
| CN110263254A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Event stage division, device, equipment and medium |
| CN110472013A (en) * | 2019-08-06 | 2019-11-19 | 湖南蚁坊软件股份有限公司 | A kind of hot topic update method, device and computer storage medium |
| CN110472013B (en) * | 2019-08-06 | 2023-03-24 | 湖南蚁坊软件股份有限公司 | Hot topic updating method and device and computer storage medium |
| CN110598151A (en) * | 2019-09-09 | 2019-12-20 | 河南牧业经济学院 | Method and system for judging news spreading effect |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109885656B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11151203B2 (en) | Interest embedding vectors | |
| Duan et al. | An empirical study on learning to rank of tweets | |
| Thakkar et al. | Approaches for sentiment analysis on twitter: A state-of-art study | |
| Zhou et al. | A classification-based approach to question routing in community question answering | |
| CN109885656A (en) | Microblogging forwarding prediction technique and device based on quantization temperature | |
| Beitzel et al. | Temporal analysis of a very large topically categorized web query log | |
| US11294974B1 (en) | Golden embeddings | |
| Luo et al. | An effective approach to tweets opinion retrieval | |
| Wu et al. | Neural news recommendation with heterogeneous user behavior | |
| CN108776671A (en) | A kind of network public sentiment monitoring system and method | |
| Cleger-Tamayo et al. | Top-N news recommendations in digital newspapers | |
| US20190266288A1 (en) | Query topic map | |
| Zhang et al. | QuestionHolic: Hot topic discovery and trend analysis in community question answering systems | |
| Paltoglou | Sentiment‐based event detection in T witter | |
| CN105488092A (en) | Time-sensitive self-adaptive on-line subtopic detecting method and system | |
| Liu et al. | Identifying web spam with user behavior analysis | |
| CN106326481A (en) | Detection method of Weibo hot topics based on suddenness | |
| Wenzhen | Personalized music recommendation algorithm based on hybrid collaborative filtering technology | |
| Xiao et al. | Predicting audience gender in online content‐sharing social networks | |
| Li et al. | Fusion convolutional attention network for opinion spam detection | |
| Chen et al. | A cloud-based recommender system-A case study of delicacy recommendation | |
| AleEbrahim et al. | Summarising customer online reviews using a new text mining approach | |
| Ramanathan et al. | Creating user profiles using wikipedia | |
| Luo et al. | Structuring T weets for improving T witter search | |
| CN105117385B (en) | A kind of method and system that public opinion information extraction is carried out based on matrix computations |
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 |