CN107369099B - User behavior analysis system facing social network - Google Patents
User behavior analysis system facing social network Download PDFInfo
- Publication number
- CN107369099B CN107369099B CN201710508599.3A CN201710508599A CN107369099B CN 107369099 B CN107369099 B CN 107369099B CN 201710508599 A CN201710508599 A CN 201710508599A CN 107369099 B CN107369099 B CN 107369099B
- Authority
- CN
- China
- Prior art keywords
- user
- forwarding
- forwarded
- behavior analysis
- social network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention provides a user behavior analysis system facing a social network, which comprises a modeling module, a forwarding behavior analysis module and a user behavior analysis module, wherein the modeling module is used for establishing a social network model, the forwarding behavior analysis module is used for analyzing the forwarding behavior of a user, the user behavior analysis module is used for analyzing the user behavior according to the forwarding behavior of the user, and the modeling module adopts the following method to establish the social network model: and representing the social network model as a binary group E ═ U, B, wherein U represents a user node set, B represents an edge set, and if a user U and a user v in the user node set concern each other, edges (U, v) exist between the user U and the user v, and the user U and the user v are adjacent nodes to each other. The invention has the beneficial effects that: the user behavior analysis of the social network is realized, specifically, the social network is modeled based on the mutual concern relationship, the junk users in the social network can be effectively eliminated, and the reliability of subsequent analysis is improved.
Description
Technical Field
The invention relates to the technical field of behavior analysis, in particular to a user behavior analysis system facing a social network.
Background
The social network is a social structure formed by individuals and related relations among the individuals, the online social network is derived from mapping of a real social network on a network space, and the online social network becomes an essential information channel for daily life of people along with rapid development of internet technology.
The user forwarding behavior is taken as a typical interaction behavior of the social network, plays an important role in the information propagation process of the social network, and greatly promotes the development of social network analysis and application.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a social network-oriented user behavior analysis system.
The purpose of the invention is realized by adopting the following technical scheme:
the utility model provides a user behavior analysis system towards social network, includes modeling module, forwarding behavior analysis module and user behavior analysis module, the modeling module is used for establishing the social network model, forwarding behavior analysis module is used for carrying out the analysis to user's forwarding behavior, user behavior analysis module is used for carrying out the analysis to user's behavior according to user's forwarding behavior, the modeling module adopts following mode to establish the social network model: and representing the social network model as a binary group E ═ U, B, wherein U represents a user node set, B represents an edge set, and if a user U and a user v in the user node set concern each other, edges (U, v) exist between the user U and the user v, and the user U and the user v are adjacent nodes to each other.
The invention has the beneficial effects that: the user behavior analysis of the social network is realized, specifically, the social network is modeled based on the mutual attention relationship, a large number of junk users in the social network can be effectively eliminated, and the accuracy and the reliability of subsequent analysis are improved.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic structural view of the present invention;
fig. 2 is a schematic structural diagram of a forwarding behavior analysis module according to the present invention.
Reference numerals:
the system comprises a modeling module 1, a forwarding behavior analysis module 2, a user behavior analysis module 3, a forwarding probability calculation unit 21, a forwarding index determination unit 22 and a forwarding behavior analysis unit 23.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1 and fig. 2, a user behavior analysis system facing a social network in this embodiment includes a modeling module 1, a forwarding behavior analysis module 2, and a user behavior analysis module 3, where the modeling module 1 is configured to establish a social network model, the forwarding behavior analysis module 2 is configured to analyze forwarding behaviors of users, the user behavior analysis module 3 is configured to analyze user behaviors according to the forwarding behaviors of the users, and the modeling module 1 establishes the social network model in the following manner: and representing the social network model as a binary group E ═ U, B, wherein U represents a user node set, B represents an edge set, and if a user U and a user v in the user node set concern each other, edges (U, v) exist between the user U and the user v, and the user U and the user v are adjacent nodes to each other.
According to the method and the device, user behavior analysis of the social network is achieved, specifically, the social network is modeled based on the mutual attention relationship, a large number of junk users in the social network can be effectively eliminated, and accuracy and reliability of follow-up analysis are improved.
Preferably, the forwarding behavior analysis module 2 includes a forwarding probability calculation unit 21, a forwarding index determination unit 22, and a forwarding behavior analysis unit 23, where the forwarding probability calculation unit 21 is configured to calculate a probability that the user publication information is forwarded, the forwarding index determination unit 22 is configured to determine a forwarding index of the user according to the probability that the user publication information is forwarded, and the forwarding behavior analysis unit 23 is configured to analyze the user forwarding behavior according to the forwarding index.
Preferably, the calculating the probability of forwarding the published information of the user specifically includes:
(1) representing all the adjacent node sets of the user u by L (u), and if the user w exists, so that w belongs to L (u) and w belongs to L (v), the user v is the close adjacent node of the user u by La(u) represents the set of all close neighbors, if user w is not present, such that w ∈ L (u) and w ∈ L (v), then user v is the loose neighbor of user u, with Lb(u) represents a set of all loose neighbor nodes;
(2) calculating the probability that the user is forwarded by the adjacent nodes:
in the formula, Pu(L (u)) represents the probability that user u is forwarded by its neighboring nodes, m (u) represents the number of messages posted by user u, ru(v) Indicating the number of messages issued by user v and forwarded by user u, tu(v) Representing the number of the users v forwarding the published messages of the users u within the set time limitL (u) represents the number of nodes adjacent to user u;
calculating the probability that the user is forwarded by the close adjacent node:
in the formula, Pu(La(u)) represents the probability that user u is forwarded by its immediately adjacent node, | La(u) | represents the number of closely adjacent nodes of user u;
calculating the probability that the user is forwarded by the loose adjacent nodes:
in the formula, Pu(Lb(u)) represents the probability that user u is forwarded by its loose neighbors, | Lb(u) | represents the number of loose neighboring nodes for user u.
The preferred embodiment considers the timeliness of the message when calculating the forwarding probability of the user message, is beneficial to improving the instantaneity of the user forwarding behavior analysis, calculates the forwarding probabilities of the close adjacent node and the loose adjacent node respectively, and is convenient for obtaining the relationship between the user forwarding behavior and the user attention relationship.
Preferably, the forwarding index determining unit 22 includes a first forwarding index determining subunit, a second forwarding index determining subunit and a forwarding index determining subunit, where the first forwarding index determining subunit is configured to determine a first forwarding index of the user, the second forwarding index determining subunit is configured to determine a second forwarding index of the user, and the forwarding index determining subunit is configured to determine the forwarding index of the user according to the first forwarding index and the second forwarding index.
The first forwarding index is obtained by the following formula:
in the formula, DYuA first forwarding index representing user u;
the second forwarding index is obtained in the following manner:
(1) for user u and its close neighbor nodes v and w, affinity is defined to reflect the degree of affinity between close neighbor nodes:
in the formula, Tu(v, w) represents the intimacy between nodes v and w, rw(v) Indicating the number of messages forwarded by user v and published by user w, rv(w) represents the number of users w forwarding user v published messages;
(2) calculating the activity of the user:
Hu＝(u)×m(u)
in the formula, HuRepresenting the activeness of the user u, and a (u) representing the average daily published message number of the user u;
(3) calculating a second forwarding index:
in the formula, DEuA second forwarding index representing user u;
the forwarding index is determined using the following equation:
in the formula (ZF)uRepresenting the forwarding index of user u.
In the preferred embodiment, the forwarding index is determined by adopting the first forwarding index and the second forwarding index, so that a more scientific and reasonable forwarding index is obtained, and a favorable guarantee is provided for the subsequent forwarding behavior analysis, so that the accuracy and the scientificity of the user behavior analysis are guaranteed.
Preferably, the analyzing the user behavior forwarding according to the forwarding index specifically includes: the larger the forwarding index of the user is, the higher the probability that the user is forwarded is, for the users with the same forwarding index and the larger the second forwarding index is, the higher the probability that the user is forwarded is, and for the users with the same second forwarding index and the larger the first forwarding index is, the higher the probability that the user is forwarded is;
the analyzing the user behavior according to the user forwarding behavior specifically comprises: the higher the probability that a user is forwarded, the greater the impact of the user in the network.
In the preferred embodiment, the forwarding index is used for analyzing the user forwarding behavior, and the forwarding behavior is used for analyzing the user behavior, so that the user behavior analysis of the social network is realized.
The user behavior analysis system oriented to the social network is adopted to analyze the user behavior, 5 social networks are selected and are compiled into the network 1, the network 2, the network 3, the network 4 and the network 5, the user behavior in the networks is analyzed, and the analysis time and the analysis accuracy of the user behavior are counted, so that compared with the existing user behavior analysis system, the beneficial effects are shown in the following table:
| reduced analysis time | Analytical accuracy improvement | |
| Network 1 | 23％ | 21％ |
| Network 2 | 25％ | 20％ |
| Network 3 | 24％ | 25％ |
| Network 4 | 26％ | 22％ |
| Network 5 | 24％ | 23％ |
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. A user behavior analysis system facing a social network is characterized by comprising a modeling module, a forwarding behavior analysis module and a user behavior analysis module, wherein the modeling module is used for establishing a social network model, the forwarding behavior analysis module is used for analyzing forwarding behaviors of users, the user behavior analysis module is used for analyzing user behaviors according to the forwarding behaviors of the users, and the modeling module adopts the following modes to establish the social network model: representing the social network model as a binary group E ═ U, B, wherein U represents a user node set, B represents an edge set, and if a user U and a user v in the user node set concern each other, edges (U, v) exist between the user U and the user v, and the user U and the user v are adjacent nodes;
the forwarding behavior analysis module comprises a forwarding probability calculation unit, a forwarding index determination unit and a forwarding behavior analysis unit, wherein the forwarding probability calculation unit is used for calculating the probability that the published information of the user is forwarded, the forwarding index determination unit is used for determining the forwarding index of the user according to the probability that the published information of the user is forwarded, and the forwarding behavior analysis unit is used for analyzing the forwarding of the user behavior according to the forwarding index.
2. The social network-oriented user behavior analysis system according to claim 1, wherein the calculating of the probability that the published information of the user is forwarded includes:
(1) representing all the adjacent node sets of the user u by L (u), and if the user w exists, so that w belongs to L (u) and w belongs to L (v), the user v is the close adjacent node of the user u by La(u) represents the set of all close neighbors, if user w is not present, such that w ∈ L (u) and w ∈ L (v), then user v is the loose neighbor of user u, with Lb(u) represents a set of all loose neighbor nodes;
(2) calculating the probability that the user is forwarded by the adjacent nodes:
in the formula, Pu(L (u)) represents the probability that user u is forwarded by its neighboring nodes, m (u) represents the number of messages posted by user u, ru(v) Indicating the number of messages issued by user v and forwarded by user u, tu(v) The number of messages issued by the user u forwarded by the user v in the set time efficiency is represented, and l (u) represents the number of nodes adjacent to the user u;
calculating the probability that the user is forwarded by the close adjacent node:
in the formula, Pu(La(u)) represents the probability that user u is forwarded by its immediately adjacent node, | La(u) | represents the number of closely adjacent nodes of user u;
calculating the probability that the user is forwarded by the loose adjacent nodes:
in the formula, Pu(Lb(u)) represents the probability that user u is forwarded by its loose neighbors, | Lb(u) | represents the number of loose neighboring nodes for user u.
3. The social network-oriented user behavior analysis system according to claim 2, wherein the forwarding index determination unit comprises a first forwarding index determination subunit, a second forwarding index determination subunit and a forwarding index determination subunit, the first forwarding index determination subunit is configured to determine a first forwarding index of the user, the second forwarding index determination subunit is configured to determine a second forwarding index of the user, and the forwarding index determination subunit is configured to determine a forwarding index of the user according to the first forwarding index and the second forwarding index.
4. The social network-oriented user behavior analysis system of claim 3, wherein the first forwarding index is obtained using the following equation:
in the formula, DYuA first forwarding index representing user u;
the second forwarding index is obtained in the following manner:
(1) for user u and its close neighbor nodes v and w, affinity is defined to reflect the degree of affinity between close neighbor nodes:
in the formula, Tu(v, w) represents the intimacy between nodes v and w, rw(v) Indicating the number of messages forwarded by user v and published by user w, rv(w) represents the number of users w forwarding user v published messages;
(2) calculating the activity of the user:
Hu＝a(u)×m(u)
where Hu represents the activity of user u, and a (u) represents the average daily number of published messages for user u;
(3) calculating a second forwarding index:
in the formula, DEuA second forwarding index representing user u;
the forwarding index is determined using the following equation:
in the formula (ZF)uRepresenting the forwarding index of user u.
5. The social network-oriented user behavior analysis system according to claim 4, wherein the user behavior forwarding is analyzed according to the forwarding index, specifically: the larger the forwarding index of the user is, the higher the probability that the user is forwarded is, for the users with the same forwarding index and the larger the second forwarding index is, the higher the probability that the user is forwarded is, and for the users with the same second forwarding index and the larger the first forwarding index is, the higher the probability that the user is forwarded is;
the analyzing the user behavior according to the user forwarding behavior specifically comprises: the higher the probability that a user is forwarded, the greater the impact of the user in the network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710508599.3A CN107369099B (en) | 2017-06-28 | 2017-06-28 | User behavior analysis system facing social network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710508599.3A CN107369099B (en) | 2017-06-28 | 2017-06-28 | User behavior analysis system facing social network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107369099A CN107369099A (en) | 2017-11-21 |
| CN107369099B true CN107369099B (en) | 2021-01-22 |
Family
ID=60305660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710508599.3A Active CN107369099B (en) | 2017-06-28 | 2017-06-28 | User behavior analysis system facing social network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107369099B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115529155A (en) * | 2022-08-05 | 2022-12-27 | 云南电网有限责任公司信息中心 | Network user behavior analysis system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799625A (en) * | 2012-06-25 | 2012-11-28 | 华为技术有限公司 | Method and system for excavating topic core circle in social networking service |
| CN103024017A (en) * | 2012-12-04 | 2013-04-03 | 武汉大学 | Method for distinguishing important goals and community groups of social network |
| CN103678671A (en) * | 2013-12-25 | 2014-03-26 | 福州大学 | Dynamic community detection method in social network |
| CN105095988A (en) * | 2015-07-01 | 2015-11-25 | 中国科学院计算技术研究所 | Method and system for detecting social network information explosion |
| CN106295702A (en) * | 2016-08-15 | 2017-01-04 | 西北工业大学 | A kind of social platform user classification method analyzed based on individual affective behavior |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9146986B2 (en) * | 2013-03-14 | 2015-09-29 | Facebook, Inc. | Systems, methods, and apparatuses for implementing an interface to view and explore socially relevant concepts of an entity graph |
-
2017
- 2017-06-28 CN CN201710508599.3A patent/CN107369099B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799625A (en) * | 2012-06-25 | 2012-11-28 | 华为技术有限公司 | Method and system for excavating topic core circle in social networking service |
| CN103024017A (en) * | 2012-12-04 | 2013-04-03 | 武汉大学 | Method for distinguishing important goals and community groups of social network |
| CN103678671A (en) * | 2013-12-25 | 2014-03-26 | 福州大学 | Dynamic community detection method in social network |
| CN105095988A (en) * | 2015-07-01 | 2015-11-25 | 中国科学院计算技术研究所 | Method and system for detecting social network information explosion |
| CN106295702A (en) * | 2016-08-15 | 2017-01-04 | 西北工业大学 | A kind of social platform user classification method analyzed based on individual affective behavior |
Non-Patent Citations (2)
| Title |
|---|
| 基于微博用户行为的数学建模和数据分析;尹子斌;《中国优秀硕士学位论文全文数据库 信息科技辑》;20130715(第7期);第I139-235页 * |
| 社交网络中节点影响力评估算法研究;王梓;《中国优秀硕士学位论文全文数据库 信息科技辑》;20150815(第8期);第I139-254页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107369099A (en) | 2017-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dahal et al. | Topic modeling and sentiment analysis of global climate change tweets | |
| CN106980692B (en) | Influence calculation method based on microblog specific events | |
| Gao et al. | A comparative study of users’ microblogging behavior on Sina Weibo and Twitter | |
| EP2498440B1 (en) | Configuration method and system of complex network and configuration and management module of server resources | |
| CN102609460B (en) | Method and system for microblog data acquisition | |
| Jahanbakhsh et al. | Social-greedy: a socially-based greedy routing algorithm for delay tolerant networks | |
| CN103795613A (en) | Method for predicting friend relationships in online social network | |
| Kibanov et al. | Temporal evolution of contacts and communities in networks of face-to-face human interactions | |
| CN104035960A (en) | Internet information hotspot predicting method | |
| CN102695121A (en) | Method and system for pushing friend information for user in social network | |
| CN104008182A (en) | Measuring method of social network communication influence and measure system thereof | |
| CN105471715A (en) | Mobile social network friend recommending method and system based on geographical position change | |
| CN103279483B (en) | A kind of topic Epidemic Scope appraisal procedure towards micro-blog and system | |
| Dou et al. | Social awareness of crisis events: A new perspective from social-physical network | |
| CN105404943A (en) | User behavior prediction method facing mobile social environment | |
| Gadek et al. | Topical cohesion of communities on Twitter | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN107369099B (en) | User behavior analysis system facing social network | |
| CN103457799A (en) | Microblog zombie user detection method based on relational graph | |
| Luo et al. | Echo chambers and segregation in social networks: Markov bridge models and estimation | |
| CN108235253A (en) | User movement dissects | |
| Sun et al. | Anomaly subgraph detection with feature transfer | |
| CN103699546A (en) | Method and device of generating IP (Internet Protocol) database of internet bar | |
| Hou et al. | Research on the behaviour and law of quantity growth of followers based on WeChat official account | |
| Shimogawa et al. | Structure of S-shaped growth in innovation diffusion |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210104 Address after: 210012 room 701, building 8, 57 Andemen street, Yuhuatai District, Nanjing City, Jiangsu Province Applicant after: Jiangsu yunjihui Software Technology Co.,Ltd. Address before: 518000 five building, fourth industrial area, Nanshan Road, Nanshan street, Nanshan District, Shenzhen, Guangdong, China, three Applicant before: SHENZHEN YUANGUANG'AN INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |