Building a TIN-LDA Model for Mining Microblog Users’ Interest

Abstract

A latent Dirichlet allocation (LDA) model is a common method for mining the interest of microblog users. But the LDA model does not reflect the hierarchical and dynamic trend of microblog users' interest. As a result, this paper combines with the timeliness and interactivity of microblog, to judge the hierarchical orientation and dynamic interest trend orientation of users' interest. And based on the dynamic interest hierarchical orientation, the three-layers interest network (TIN-LDA) model is constructed to mine the interest of microblog users. In addition, this model expands interest attributes. Interest attributes include contents, contents marked with special symbols, forwarding contents, along with the authentication user name and authentication information. Bringing the interest attributes into users' interest analysis so as to improve the accuracy of mining microblog users' interest keywords and topics. Topic quality assessment and perplexity evaluation were used to verify the effectiveness of the TIN-LDA model in mining the interest of microblog users.