Microblog big data interest community analysis optimization method based on user experience

Abstract

The present invention relates to a microblog big data interest community analysis optimization method based on a user experience. The method comprises a step of carrying out weighted reconfiguration of an original microblog network, a step of completing the community division of the reconfigured weighted network based on the discovery algorithm of a link community, and a step of using a hierarchical clustering algorithm to continuously merge two communities with a largest similarity, finally forming a link community through division, and generating a tree-shaped hierarchical diagram. Starting from aspects of interest modeling and community discovery, through analysing microblog content and a user behavior, a user is helped to find interested users and topics of the user. Compared with a traditional method, the accuracy, recall ratio and F value of the method of the invention are improved significantly.

Description

technical field [0001] The invention relates to network data analysis, in particular to a method for analyzing and optimizing microblog big data interest communities based on user experience. Background technique [0002] At present, social networks are increasingly favored by the public, and user activity is also increasing. Among them, Weibo, a typical application, is loved by the public because of its openness and quickness. However, with the gradual expansion of the user scale and the continuous generation of massive information on the network, users will face the problem of information flooding. It becomes more and more difficult to find people or things they are interested in in the vast amount of data. For most users, users prefer to establish contact with people with the same interests and hobbies on Weibo and gain attention, but Weibo users are mostly strangers and lack of understanding with each other. It is difficult to find strangers with similar interests in a...

AI Technical Summary

Problems solved by technology

[0005] Through the research, it is found that the microblog network community has the following characteristics: first, there are isolated nodes in the community, which means that such nodes do not have a "following" relationship with other users, but are more interested in relevant content in the community; The network density is small and the structure is sparse, which is contrary to the characteristics of high network density and close connection between users required by traditional complex network communities; thirdly, the connection in the microblog network is established by the attention mechanism between users, but this This connection does not mean that there must be similar attributes between users, on the contrary, there may be large differences

In summary, it can be seen that only relying on the network structure for community discovery is not effective.

[0006] In addition, if we start from the perspective of network node content, we will find that there is a lot of noise in the node content information, which is not conducive to the discovery of interest, especially the critical point in the network cannot be identified

Images