Research on the Impact of Online Public Opinion on College Students' Mental Health — A Natural Language Processing–Based Approach
DOI:
https://doi.org/10.62051/ez39nt17Keywords:
Online public opinion; college students; mental health; sentiment analysis; CNN-LSTM.Abstract
As the Internet becomes deeply integrated into college students’ daily lives,online public opinion has become an important factor influencing their mental health.This study investigates its impact on college students by collecting textual data from news comments,Weibo,Zhihu,and university forums.Using high-frequency word analysis,word-cloud visualization,and sentiment analysis,CNN and CNN-LSTM models were developed to examine topics including online culture,online gaming,cyberbullying,online social networking, mental health, public opinion governance, and online discourse.The results show that negative sentiment outweighs positive and neutral sentiment in online discussions and tends to generate greater engagement,as reflected in higher numbers of comments and likes.In particular,cyberbullying, online gaming,online social networking,and online discourse emerge as key negative factors affecting college students’ mental health.The CNN-LSTM model also outperformed the CNN model in sentiment classification.The findings suggest that universities should strengthen online public opinion guidance, improve mental health services, and enhance students’ information literacy and emotional regulation.
Downloads
References
[1] Hu Zhiwei. An Analysis of the Basic Principles for Handling Online Public Opinion Incidents: Taking the Response to the “Rat Head, Duck Neck” Online Public Opinion Case as an Example[J]. Haihe Media, 2024(05): 74–76.
[2] Xu Zixian, Dong Beifei. The Current Situation, Causes, and Governance Paths of Textbook-Related Online Public Opinion in the Social Media Era: An Analysis of 17 Online Public Opinion Cases Since the New Curriculum Reform[J]. Shanghai Educational Research, 2025(08): 44–51.
[3] Liu Yanfang, Wang Pengyao. Research on the Regulatory Mechanism of Online Public Opinion Based on Evolutionary Game Theory[J]. Information Exploration, 2021(11): 16–24.
[4] Cilizoglu, M., Tokdemir, E., & Zarpli, O. (2025). To punish or to reward? The effect of sanction threats on public opinion. International Interactions, 51(4), 668–688. DOI: https://doi.org/10.1080/03050629.2025.2518382
[5] Ісмаїлзаде, Л. (2023). Медіа, маніпуляція та інформаційна війна. Grani, 26(5), 55–65. DOI: https://doi.org/10.15421/1723102
[6] Lippmann W. Public Opinion[M]. New York: Harcourt, Brace and Company, 1922.
[7] Habermas J. The Structural Transformation of the Public Sphere: An Inquiry into a Category of Bourgeois Society[M]. Cambridge, MA: The MIT Press, 1989.
[8] McLuhan M. Understanding Media: The Extensions of Man[M]. New York: McGraw-Hill, 1964.
[9] Burcu Bayram, A., Keels, E., & Tokdemir, E. (2024). Enforcement of international human rights law: A comparative exploration of alternative public opinion channels. The British Journal of Politics and International Relations, 27(4), 1385–1407. DOI: https://doi.org/10.1177/13691481241305975
[10] Sunstein C R. #Republic: Divided Democracy in the Age of Social Media[M]. Princeton, NJ: Princeton University Press, 2017. DOI: https://doi.org/10.1515/9781400884711
[11] DOUAI, A. (2009). Media ethics in international conflict. The Journal of International Communication, 15(2), 79–96. DOI: https://doi.org/10.1080/13216597.2009.9674752
[12] China Internet Network Information Center. The 56th Statistical Report on China’s Internet Development[EB/OL]. 2025-07-21.
[13] Sun Xu. Research on the Influence of Online Public Opinion on College Students’ Values and Countermeasures[D]. Hebei Normal University, 2023.
[14] Ji Fajia, Zhu Ying, Yin Hao, et al. Research on Natural Language Processing Technology Based on Hybrid Neural Networks[J]. Electronic Design Engineering, 2023, 31(10): 92–96. DOI: 10.14022/j.issn1674-6236.2023.10.020.
[15] Jin Yihan, Wei Chuang, Tang Yuzhe, et al. An Online Milling Chatter Monitoring Method Based on Multi-Channel Parallel Convolutional Neural Networks and Attention Mechanism[J]. Machine Design and Research, 2025, 41(04): 22–29.
[16] Wang Bingmei, Zhang Ye, Li Shubin, et al. An Abnormal Data Detection Model for New Distribution Networks Based on a CNN-LSTM Hybrid Network[J]. Acta Energiae Solaris Sinica, 2025, 46(05): 243–250.
[17] Zou Congrui. Research on Key Issues in Sentiment Prediction for Multi-turn Text Dialogues[D]. Chongqing University, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Transactions on Social Science, Education and Humanities Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
