Method and system of discovering and analyzing structures of user groups in microblog

Patent metadata

Field	Value
Publication number	US-10078802-B2
Application number	US-201314760051-A
Country	US
Kind code	B2
Filing date	Nov 11, 2013
Priority date	Jan 9, 2013
Publication date	Sep 18, 2018
Grant date	Sep 18, 2018

Abstract

A method and system of discovering and analyzing structures of user groups in a microblog is provided in this invention. The method of discovering and analyzing structures of the user groups in a microblog comprises: acquiring information on behavior data of microblog users of a target group; constructing a microblog user association network based on the information on behavior data of the microblog users of the target group; acquiring at least one maximal clique from the microblog user association network; acquiring at least one core clique based on the maximal clique; and conducting behavior analysis on the user groups in the microblog based on the acquired maximal clique and/or the acquired core clique. Using the method and system of discovering and analyzing structures of user groups in a microblog provided in this invention, complicated relationships among microblog users may be sufficiently identified and the speed of discovering and analyzing structures of user groups in a microblog may be improved to meet the demand for large scaled data processing.

First claim

The invention claimed is:

1. A method performed by a processor of discovering and analyzing structures of user groups in a microblog, characterized in comprising:
acquiring, by the processor, information on behavior data of microblog users of a target group;
constructing, by the processor, a microblog user association network based on the information on behavior data of the microblog users of the target group;
acquiring, by the processor, at least one maximal clique from the microblog user association network;
acquiring, by the processor, at least one core clique based on the maximal clique;
conducting, by the processor, behavior analysis on the user groups in the microblog based on the acquired maximal clique and/or the acquired core clique,
wherein the step of acquiring, by the processor, at least one maximal clique particularly comprises:
acquiring, by the processor, all maximal cliques of the microblog user association network by utilizing a search-triangle based method operated with a certain pruning strategy, and
wherein the step of acquiring, by the processor, at least one core clique particularly comprises:
based on the maximal cliques, analyzing, by the processor, a social relation circle of each microblog user and all other microblog users, and filtering out, by the processor, the core cliques of the microblog user association network based on an inclusion-consolidation strategy on the social relation circles, wherein if a social relation circle of one microblog user is not included by any of the other social relation circles, the social relation circle of the one microblog user is filtered out as one of the core cliques.

2. The method of discovering and analyzing structures of user groups in a microblog according to claim 1 , characterized in that, the step of constructing, by the processor, a microblog user association network comprises:
establishing, by the processor, association relationships among the microblog users by utilizing an association relationship evaluation model, based on the information on behavior data of the microblog users of the target group; and
constructing, by the processor, the microblog user association network which is composed of a microblog user used as a node and an association relationship used as an edge, based on the established association relationships among the microblog users.

3. The method of discovering and analyzing structures of user groups in a microblog according to claim 1 , characterized in that, the step of acquiring at least one core clique further comprises:
acquiring, by the processor, a common microblog user existing among the core cliques;
re-partitioning, by the processor, the common microblog user into a corresponding core clique such that there is no common microblog user among respective core cliques.

4. The method of discovering and analyzing structures of user groups in a microblog according to claim 3 , characterized in that, the method further comprises:
based on the core cliques, merging, by the processor, remaining users in the microblog user association network into a corresponding nearest network core clique in accordance with a certain distance definition;
consolidating, by the processor, the core cliques of the microblog user association network by utilizing a hierarchical clustering algorithm to obtain a final structure partition on the user groups in the microblog.

5. A system of discovering and analyzing structures of user groups in a microblog, which comprises a processor, characterized in that the processor is configured to perform the operations of:
acquiring information on behavior data of microblog users of a target group;
constructing a microblog user association network based on the information on behavior data of the microblog users of the target group;
acquiring at least one maximal clique from the microblog user association network;
acquiring at least one core clique based on the maximal clique;
conducting behavior analysis on the user groups in the microblog based on the acquired maximal clique and/or the acquired core clique,
wherein the operation of acquiring at least one maximal clique particularly comprises:
acquiring all maximal cliques of the microblog user association network by utilizing a search-triangle based method operated with a certain pruning strategy,
and wherein the operation of acquiring at least one core clique particularly comprises:
based on the maximal cliques, analyzing a social relation circle of each microblog user and all other microblog users, and filtering out the core cliques of the microblog user association network based on an inclusion-consolidation strategy on the social relation circles, wherein if a social relation circle of one microblog user is not included by any of the other social relation circles, the social relation circle of the one microblog user is filtered out as one of the core cliques.

6. The system of discovering and analyzing structures of user groups in a microblog according to claim 5 , characterized in that, the operation of acquiring information on behavior data of microblog users of a target group comprises: establishing association relationships among the microblog users by utilizing an association relationship evaluation model, based on the information on behavior data of the microblog users of the target group; and constructing the microblog user association network which is composed of a microblog user used as a node and an association relationship used as an edge, based on the established association relationships among the microblog users.

7. The system of discovering and analyzing structures of user groups in a microblog according to claim 5 , characterized in that, the operation of acquiring at least one core clique further comprises: acquiring a common microblog user existing among the core cliques; re-partitioning the common microblog user into a corresponding core clique such that there is no common microblog user among respective core cliques.

8. The system of discovering and analyzing structures of user groups in a microblog according to claim 7 , characterized in that, the processor is further configured to perform the operations of:
based on the core cliques, merging remaining users in the microblog user association network into a corresponding nearest network core clique in accordance with a certain distance definition;
consolidating the core cliques of the microblog user association network by utilizing a hierarchical clustering algorithm to obtain a final structure partition on the user groups in the microblog.

Assignees

• Univ Peking Founder Group Co
• Univ Beijing
• Beijing Founder Electronics Co Ltd

Inventors

• Zhao Liyong
• Yu Xiaoming
• Yang Jianwu
• Zheng Yan

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/958 Primary

  Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking · CPC title

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• H04L51/32

  Electricity · mapped topic

• G06N5/04 Primary

  Inference or reasoning models · CPC title