Research Article
UR Rank: Micro-blog User Influence Ranking Algorithm Based on User Relationship
184 downloads
@INPROCEEDINGS{10.1007/978-3-030-00916-8_37, author={Wenbin Yao and Yiwei Yang and Dongbin Wang}, title={UR Rank: Micro-blog User Influence Ranking Algorithm Based on User Relationship}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 13th International Conference, CollaborateCom 2017, Edinburgh, UK, December 11--13, 2017, Proceedings}, proceedings_a={COLLABORATECOM}, year={2018}, month={10}, keywords={Micro-blog User influence Support vector regression PageRank}, doi={10.1007/978-3-030-00916-8_37} }- Wenbin Yao
Yiwei Yang
Dongbin Wang
Year: 2018
UR Rank: Micro-blog User Influence Ranking Algorithm Based on User Relationship
COLLABORATECOM
Springer
DOI: 10.1007/978-3-030-00916-8_37
Abstract
In this paper, a novel UR Rank (User Relationships based Ranking) algorithm is proposed for ranking the influence of the user. We first explore five factors that affect user relationship. They are following rate () factor, activity () factor, authority () factor, interaction () factor and similarity () factor. Then those factors are used in Support Vector Regression (SVR) model to predict the relationship between users. We assimilate such predicted relationship into a PageRank based transition probability to identify influential users. The experiments on a real micro-blog data set demonstrate that UR Rank algorithm has better performance and is more persuasive than the existing algorithms.
Copyright © 2017–2025 EAI
