Research Article
User Influence Analysis Model for Weibo Topics
@INPROCEEDINGS{10.4108/eai.26-5-2023.2334300, author={Guixian Xu and Yuan Tian and Yueting Meng}, title={User Influence Analysis Model for Weibo Topics}, proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China}, publisher={EAI}, proceedings_a={MSEA}, year={2023}, month={7}, keywords={social network weibo topics user influence emotional tendencies pagerank}, doi={10.4108/eai.26-5-2023.2334300} }- Guixian Xu
Yuan Tian
Yueting Meng
Year: 2023
User Influence Analysis Model for Weibo Topics
MSEA
EAI
DOI: 10.4108/eai.26-5-2023.2334300
Abstract
Due to the openness of social media, public opinion events are often triggered. Identifying important users in hot topics is helpful to correctly guide public opinion and create a green online environment. Directed at the fact that the existing methods fail to consider the influence of users' followers and the influence of comment sentiment tendencies, a user influence analysis model for Weibo based on user information and content information - UCRank (user-content influence rank) - was proposed. The model takes into account four factors, users self-influence, followers-influence, content information and comment sentiment polarity, to jointly quantify the user influence. Experimental results show that the proposed model has the best performance in terms of precision, recall and F1 value when compared with other traditional algorithms.