Research on the evolution of netizens’ comment focus in university online public opinion: KTF-BTM topic model with topic-temporal-focus framework

Frontiers in Physics

Physics

Yang Zhang¹  Ji-Qing Lian²  Ren-De Li³  Hong-Tao Duan⁴ 

[1] Business School, University of Shanghai for Science and Technology, Shanghai, China;Department of Printing and Packaging Engineering, Shanghai Publishing and Printing College, Shanghai, China;Library, University of Shanghai for Science and Technology, Shanghai, China;Shanghai Center for Research and Development of Cyberculture in Education (SCRDCE), Shanghai, China;

关键词: topic modeling;    BTM;    university public opinion;    social media;    microblog;   

DOI  :  10.3389/fphy.2023.1251386

 received in 2023-07-01, accepted in 2023-08-15,  发布年份 2023

来源: Frontiers

【 摘 要 】

Nowadays, Study of comments in MicroBlog online public opinion is of great significance for relevant departments in managing public opinion, due to the increasing influence of online public opinion on the Internet. This paper presents a method for studying the evolutionary characteristics of netizens’ comment focus in university online public opinion. This method is based on a three-stage framework called Topic-Temporal-Focus. Firstly, in the topic mining stage, the KTF-BTM model is proposed for topic recognition, which effectively improves the quality of analysis. Secondly, in the temporal segmentation stage, time periods are divided into 4-hour intervals, and the identified topics are paired with each comment text to generate a topic-temporal list. Finally, in the focus recognition stage, the content and evolution patterns of netizens’ comment focus within shorter time sequences are explored by analyzing the data characteristics of the topic-temporal list. Experimental results show that the proposed KTF-BTM model significantly enhances topic recognition quality for short texts. The Topic-Temporal-Focus framework overcomes the challenge of sparse comment text data within shorter time periods and effectively classifies topic evolution within limited time sequences. This research work serves as a valuable contribution towards understanding the evolutionary characteristics of netizens’ focal points in university online public opinion.

【 授权许可】

Unknown   
Copyright © 2023 Zhang, Lian, Li and Duan.