Improved PageRank Algorithm Combined User Behavior with Topic Similarity

Hao-dong ZHU, Bao-feng HE
2017 DEStech Transactions on Computer Science and Engineering  
Aiming at shortcomings of the drifting theme and the splitting page weight of traditional PageRank algorithm, an improved PageRank algorithm combined user behavior with topic similarity was proposed. Combined with the time factor, the proposed algorithm comprehensively analyzed retweet, comment and mention, measured contribution of three kinds of different behaviors for micro-blog user influence by means of statistical analysis, and used improved TF-IDF calculate the weight of subject relevance
more » ... to choose pages with higher correlation degree and obtain different PR value. The simulation results show that compared with Micro-blog's common sorting algorithms, the improved PageRank algorithm has better sorting effect.
doi:10.12783/dtcse/aita2016/7578 fatcat:r466r2asnzcchdhkysmja5jo4m