CN110008406A - A kind of public sentiment personalized recommendation algorithm based on similar community - Google Patents
A kind of public sentiment personalized recommendation algorithm based on similar community Download PDFInfo
- Publication number
- CN110008406A CN110008406A CN201910275404.4A CN201910275404A CN110008406A CN 110008406 A CN110008406 A CN 110008406A CN 201910275404 A CN201910275404 A CN 201910275404A CN 110008406 A CN110008406 A CN 110008406A
- Authority
- CN
- China
- Prior art keywords
- user
- neighbours
- public sentiment
- similar
- similarity
- 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.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000007418 data mining Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 235000019640 taste Nutrition 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 claims description 2
- 239000012141 concentrate Substances 0.000 abstract description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000009423 ventilation Methods 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention proposes a kind of public sentiment personalized recommendation algorithm based on similar community, include the following steps: the thought based on similar community, by calculating the discovery and data mining of similar community based on figure, user characteristics are extracted in analysis, form " neighbours " collection of similar users.Wherein, the similarity between user is calculated according to features described above.Similarity value is found out according to the methods of cosine similarity, associated similarity, and then sorts and forms nearest " neighbours " collection of target user.Recommended according to " neighbours " user.Wherein, prediction and evaluation is carried out to public sentiment topic according to the user that its " neighbours " concentrate, the public sentiment topic for evaluating high is recommended into user.A kind of public sentiment personalized recommendation algorithm based on similar community realizes the user characteristics by extracting similar community, form " neighbours " collection of similar users, " neighbours " user is recommended using similar users group interest and the collaborative filtering method of behavior, to improve the accuracy of commending contents, while also extending content covering surface.
Description
Technical field
The present invention relates to figure calculating, community network, data mining and personalized recommendations, and in particular to a kind of based on similar
The public sentiment personalized recommendation algorithm of community.
Background technique
User faces numerous many and diverse public feelings informations and resource in community network, how quickly and easily to obtain oneself sense
The public feelings information of interest is extremely important, and at this moment just there is an urgent need to a kind of public sentiment recommendation of personalized information clothes for being suitble to oneself by user
Business.So-called personalized ventilation system is exactly according to the information requirement of user, interest and behavior pattern etc., by the interested letter of user
Breath, products & services recommend the information service of user.
Personalized recommendation algorithm can be divided into the algorithm etc. of rule-based algorithm and Cempetency-based education.It is rule-based
Algorithm, rule can be customized by user, can use the digging technology based on dependency rule also to find, recommendation information depends on
The quality and quantity of rule.The advantages of this algorithm be it is simple, direct, the disadvantage is that increasing with regular quantity, system will become
It is increasingly difficult to manage.Content-based filtering algorithm is to filter information using resource and the similitude of user interest, this calculation
Method advantage is simple, effective, the disadvantage is that interested content that cannot be new for user's discovery.
Compared to other personalized recommendation algorithms, the personalized recommendation algorithm based on similar community can be by similar use
The division of family group realizes information sifting by " neighbours " user group, effectively improves the accuracy of commending contents, while also expanding
The covering surface of institute's recommendation information is opened up.
In conclusion the basic thought of the public sentiment personalized recommendation algorithm based on similar community are as follows: by being calculated based on figure
User characteristics are extracted in the discovery and data mining of similar community, analyze the essential attributes such as user behavior and hobby, pass through
Corresponding calculating formula of similarity calculates the similitude between user, forms " neighbours " collection of similar users, using have similar tastes and interests,
Possess the hobby of the group of common experience to recommend " neighbours " user.
Summary of the invention
To solve shortcoming and defect in the prior art, the invention proposes a kind of, and the public sentiment based on similar community is personalized
Proposed algorithm can carry out feature to the user of similar community by calculating the discovery and data mining of similar community based on figure
Extraction, analysis user is to the essential attribute of the historical viewings behavioural information of certain public sentiment topic or evaluation and user (including year
Age, gender, hobby), the similitude between user is calculated by corresponding calculating formula of similarity, forms similar users
" neighbours " collection.Recommended according to " neighbours " user.The algorithm of collaborative filtering is had similar tastes and interests using certain, possesses common experience
The hobby of group carry out the interested public feelings information of recommended user, individual is given information considerable degree of time by the mechanism of cooperation
It answers (as evaluated), and records to achieve the purpose that filtering and then help others' filter information.
The technical solution of the present invention is as follows:
A. data initialization.Data initialization mainly initializes evaluation data of the user to public sentiment topic.Structure
The relational matrix of user and public sentiment topic, i.e. evaluations matrix are built, while removing redundant items.
B. the formation of nearest-neighbors collection.The similarity between user is calculated according to above-mentioned relation.According to cosine similarity,
The methods of associated similarity finds out similarity value, and then sorts and form nearest " neighbours " collection of target user.
C. prediction and evaluation and generation recommendation results." neighbours " collection of target user can be obtained by similarity height, so
Prediction and evaluation is carried out to public sentiment topic according to the user that its " neighbours " concentrate afterwards, the public sentiment topic for evaluating high is recommended into user.
Beneficial effects of the present invention:
(1) discovery and data mining that similar community is calculated based on figure are constructed, by extracting the user characteristics of similar community,
" neighbours " collection for forming similar users realizes that more accurately public feelings information is recommended to " neighbours " user;
(2) this method is pushed away by the collaborative filtering method based on similar users group interest and behavior for personalization
It recommends, to improve the accuracy of commending contents, while also extending content covering surface.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of structure chart of the public sentiment personalized recommendation algorithm based on similar community of the present invention;
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, the detailed process to a kind of public sentiment personalized recommendation algorithm based on similar community carries out specifically
It is bright.
A. data initialization
Data initialization mainly initializes evaluation data of the student to public sentiment topic.Construct student and public sentiment words
The relational matrix of topic, i.e. evaluations matrix, while removing redundant items.
B. the formation of nearest-neighbors collection
The similarity between user is calculated according to above-mentioned relation.It is asked according to the methods of cosine similarity, associated similarity
Similarity value out, and then sort and form nearest " neighbours " collection of target user.
C. prediction and evaluation and generation recommendation results
" neighbours " collection of target user, the user couple then concentrated according to its " neighbours " can be obtained by similarity height
Public sentiment topic carries out prediction and evaluation, and the public sentiment topic for evaluating high is recommended user.Evaluation and foreca calculation formula is as follows:
In formula:Rv --- respectively represent user u, the average value that v evaluates all public sentiment topics.
A kind of public sentiment personalized recommendation algorithm based on similar community of the invention, by figure calculate, data mining and
Similar users can be incorporated into and be come by the combination of community network, this method, and individual is helped to filter out required public sentiment by group
Information avoids the deficiency for only relying on sole user's behavioral data to carry out public feelings information recommendation.Again by being based on similar users
Group interest and the collaborative filtering method of behavior are used for personalized recommendation, substantially increase the accuracy of commending contents, simultaneously
Also content covering surface is extended.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (1)
1. a kind of public sentiment personalized recommendation algorithm based on similar community, which is characterized in that by calculating similar community based on figure
Discovery and data mining, can to the user of similar community carry out feature extraction, analysis user certain public sentiment topic is gone through
The essential attribute (including age, gender, hobby) of history browsing behavior information or evaluation and user, pass through corresponding phase
The similitude between user is calculated like degree calculation formula, forms " neighbours " collection of similar users.It is carried out according to " neighbours " user
Recommend.The algorithm of collaborative filtering be had similar tastes and interests using certain, possessed common experience group hobby it is interested come recommended user
Public feelings information, individual gives that information is considerable degree of to respond (as evaluation) by the mechanism of cooperation, and records to reach
The purpose of filtering helps others' filter information in turn, comprising the following steps:
A. data initialization
Data initialization mainly initializes evaluation data of the student to public sentiment topic.Construct student and public sentiment topic
Relational matrix, i.e. evaluations matrix, while removing redundant items.
B. the formation of nearest-neighbors collection
The similarity between user is calculated according to above-mentioned relation.Phase is found out according to the methods of cosine similarity, associated similarity
Like angle value, and then sorts and form nearest " neighbours " collection of target user.
C. prediction and evaluation and generation recommendation results
" neighbours " collection of target user can be obtained by similarity height, the user then concentrated according to its " neighbours " is to public sentiment
Topic carries out prediction and evaluation, and the public sentiment topic for evaluating high is recommended user.Evaluation and foreca calculation formula is as follows:
In formula:Rv --- respectively represent user u, the average value that v evaluates all public sentiment topics.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910275404.4A CN110008406A (en) | 2019-04-04 | 2019-04-04 | A kind of public sentiment personalized recommendation algorithm based on similar community |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910275404.4A CN110008406A (en) | 2019-04-04 | 2019-04-04 | A kind of public sentiment personalized recommendation algorithm based on similar community |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110008406A true CN110008406A (en) | 2019-07-12 |
Family
ID=67170157
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910275404.4A Pending CN110008406A (en) | 2019-04-04 | 2019-04-04 | A kind of public sentiment personalized recommendation algorithm based on similar community |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110008406A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472147A (en) * | 2019-07-29 | 2019-11-19 | 天闻数媒科技(湖南)有限公司 | It is a kind of to provide the method and its system of personalized examination question based on recommended engine |
CN116364261A (en) * | 2023-06-02 | 2023-06-30 | 北京小懂科技有限公司 | Intelligent recommendation method, system, equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016191959A1 (en) * | 2015-05-29 | 2016-12-08 | 深圳市汇游智慧旅游网络有限公司 | Time-varying collaborative filtering recommendation method |
CN107862012A (en) * | 2017-10-30 | 2018-03-30 | 江苏大学 | A kind of information resources auto recommending method for group of college students |
-
2019
- 2019-04-04 CN CN201910275404.4A patent/CN110008406A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016191959A1 (en) * | 2015-05-29 | 2016-12-08 | 深圳市汇游智慧旅游网络有限公司 | Time-varying collaborative filtering recommendation method |
CN107862012A (en) * | 2017-10-30 | 2018-03-30 | 江苏大学 | A kind of information resources auto recommending method for group of college students |
Non-Patent Citations (1)
Title |
---|
王洁,汤小春: "基于社区网络内容的个性化推荐算法研究 王洁,汤小春 (" * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472147A (en) * | 2019-07-29 | 2019-11-19 | 天闻数媒科技(湖南)有限公司 | It is a kind of to provide the method and its system of personalized examination question based on recommended engine |
CN116364261A (en) * | 2023-06-02 | 2023-06-30 | 北京小懂科技有限公司 | Intelligent recommendation method, system, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hsu | A personalized English learning recommender system for ESL students | |
CN102982042B (en) | A kind of personalization content recommendation method, platform and system | |
Yu et al. | Adaptive social similarities for recommender systems | |
CN103034508A (en) | Software recommending method and software recommending system | |
Pratt | Four wine tourist profiles | |
WO2009126815A2 (en) | Diversified, self-organizing map system and method | |
CN106604051A (en) | Live channel recommending method and device | |
KR20130090344A (en) | Apparatus, system, method and computer readable recording media storing the program for related recommendation of tv program contents and web contents | |
CN103686382A (en) | Program recommendation method | |
CN108650532B (en) | Cable television on-demand program recommendation method and system | |
CN104620267A (en) | Method and apparatus for inferring user demographics | |
CN108334592A (en) | A kind of personalized recommendation method being combined with collaborative filtering based on content | |
CN107563343A (en) | The self-perfection method and system of FaceID databases based on face recognition technology | |
KR101804967B1 (en) | Method and system to recommend music contents by database composed of user's context, recommended music and use pattern | |
CN107590232A (en) | A kind of resource recommendation system and method based on Network Study Environment | |
Sidana et al. | Learning to recommend diverse items over implicit feedback on PANDOR | |
CN116595398A (en) | Resource intelligent matching method and related device based on meta universe | |
CN106202570A (en) | A kind of user information acquiring method and device | |
Dhillon et al. | Modeling dynamic user interests: A neural matrix factorization approach | |
CN107341199A (en) | A kind of recommendation method based on documentation & info general model | |
CN110008406A (en) | A kind of public sentiment personalized recommendation algorithm based on similar community | |
JP2014106943A (en) | Group extraction device, group extraction method, and program | |
US20130108180A1 (en) | Information processing device, information processing method, and program | |
Tsutsumi et al. | Towards business partnership recommendation using user opinion on Facebook | |
Pramanik et al. | Can i foresee the success of my meetup group? |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190712 |