Shu Wu1, Xiaobei Wang1, Hongwei Yu1, Xucong Zhang1, Weiyang Xia1, Dingyi Cheng1, Alia Erbolat2, Beibei Tang3, Kangrui Sun4
1Sino-German College, University of Shanghai for Science and Technology, Shanghai, China
2School of Journalism and Communication, Shanghai University, Shanghai, China
3Golden Concord Holdings, Suzhou, China
4Yizhu Intelligent Technology, Hangzhou, China
In the context of media public opinion becoming the determination of people's views and behaviors, the analysis and control of public opinion has become an important part of understanding the needs and demands of the public and maintaining the stability of the public mood.  This project aims to use the program algorithm to obtain the remarks related to the specified event in online social media (microblog), and analyze it through the algorithm, so as to provide a complete map of the development trend and tendency of public opinion events, and provide reference for the development and coping strategies under the current time node. In response to the comments on Weibo (Sichuan Middle School Incident), the program uses algorithms such as text detection, exception filtering, sorting, and self-designed and trained neural networks to automatically obtain information, establish subjects and time nodes, Analyze the proportion of different public opinion development tendencies and output them in the form of maps, reduce the expenditure of human resources, effectively reduce the emotional bias in the process of obtaining public opinion information, effectively and rationally analyze the tendency and evolution direction of public opinion, show the dynamic evolution process, and provide theoretical reference for response and governance.
public opinion, reference for the development, Circulation of Industrial Data, Shanghai
Shu Wu, Xiaobei Wang, Hongwei Yu, Xucong Zhang, Weiyang Xia, Dingyi Cheng, Alia Erbolat, Beibei Tang, Kangrui Sun. Respond to Weibo Comments While Incorporating the Sentiment Evolution Trend Depicted by a Sankey Chart. International Journal of Frontiers in Sociology (2023), Vol. 5, Issue 13: 26-30. https://doi.org/10.25236/IJFS.2023.051305.
 Chen J, Gong Z, Liu W. A. Dirichlet process biterm-based mixture model for short text stream clustering [J]. Applied Intelligence, 2020, 50 (5): 1609-1619.
 Nimala K, Jebakumar R. A. Robust User Sentiment Biterm Topic Mixture Model Based on User Aggregation Strategy to Avoid Data Sparsity for Short Text [J]. Journal of Medical Systems, 2019, 43 (4).
 Zhu L, Xu H, Xu Y, et al. A joint model of extended LDA and IBTM over streaming Chinese short texts [J]. Intelligent Data Analysis, 2019, 23 (3): 681-699.
 Murshed B A H, Abawajy J, Mallappa S, et al. Enhancing Big Social Media Data Quality for Use in Short-Text Topic Modeling[J]. Ieee Access, 2022, 10: 105328-105351.
 Deng Xiaolu, Yao Song. Research on Sina Weibo data crawler based on Scrapy [J]. Modern Information Technology, 2023, 7(03):44-47. DOI:10. 19850/j. cnki. 2096-4706. 2023. 03. 010