Deep Learning-Based Prediction of Polarization in Social Media Among Youth
Main Article Content
Abstract
The stochastic nature of youth social media polarization poses challenges for traditional early-stage prediction. This study constructs a heterogeneous temporal network to represent multifaceted interactions among users, text, and hashtags, treating the evolution of online opinion as a spatiotemporal signal-propagation process in networked communication environments. Based on the DyGCN-GRU framework, the model captures the spatiotemporal propagation patterns of public-opinion evolution, integrates sentiment kurtosis, semantic variance, and community opposition density to generate polarization-intensity sequences, and finally employs a Transformer decoder to predict polarization risk. The network incorporates platform-specific embeddings, youth-oriented semantic features, and behavioral attributes to improve the detection of weak early signals. Experimental results on Weibo and Zhihu data show that the proposed method achieves an F1-score of 0.915, a root mean square error of 0.068, and an early-warning lead time of 11.3 minutes. The results verify the model’s ability to quantitatively perceive and dynamically predict early risks of youth public-opinion polarization, and provide a technical basis for online risk monitoring and intelligent information-governance systems.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
M. S. Alam, M. S. H. Mrida, and M. A. Rahman, “Sentiment analysis in social media: How data science impacts public opinion knowledge integrates natural language processing (NLP) with artificial intelligence (AI),” American Journal of Scholarly Research and Innovation, vol. 4, no. 01, pp. 63-100, 2025, doi: 10.63125/r3sq6p80.
M. Mudhofi, I. Supena, A. Karim, et al., “Public opinion analysis for moderate religious: Social media data mining approach,” Jurnal Ilmu Dakwah, vol. 43, no. 1, pp. 1-27, 2023, doi: 10.21580/jid.v43.1.16101.
P. L. Kharvi, “Understanding the impact of AI-generated deepfakes on public opinion, political discourse, and personal security in social media,” IEEE Security & Privacy, vol. 22, no. 4, pp. 115-122, 2024, doi: 10.1109/MSEC.2024.3405963.
S. Arifin and J. A. Rojak, “Social Media and Public Opinion Formation: Information Dissemination and Polarization,” Journal of Social Science Studies, vol. 2, no. 1, pp. 139-142, 2022.
W. Mengke and L. Gang, “Research on the construction of quantitative index of microblog group polarization in university public opinion events,” The Journal of Engineering, vol. 2022, no. 3, pp. 285-294, 2022, doi: 10.1049/tje2.12113.
C. Juditha, “The Phenomenon of ‘Indonesia Gelap’ on Social Media: Sentiment Analysis and Public Opinion Polarization,” Jurnal Komunikasi, vol. 17, no. 1, pp. 157-170, 2025, doi: 10.24912/jk.v17i1.33846.
U. Javed and U. Javed, “The influence of social media algorithms on political polarization and public opinion,” Online Media and Society, vol. 4, no. 2, pp. 44-52, 2023, doi: 10.71016/oms/2ffw9391.
H. R. Prabayanti and P. S. Nabilah, “Digital Cultural Practices and Public Opinion Polarization in the #KaburAjaDulu Narrative on Social Media,” International Journal of Communication, Media, and Development Studies, vol. 3, no. 1, pp. 39-47, 2026.
A. Ashraf, K. S. Gondal, and S. Ahmed, “Social Media and Political Polarization: Investigating the Role of Online Platforms in Shaping Public Opinion,” Journal of Development and Social Sciences, vol. 6, no. 1, pp. 705-717, 2025, doi: 10.47205/jdss.2025(6-I)61.
M. Siddique and A. Tariq, “The Impact of Social Media on Political Polarization and Public Opinion in Democratic Societies,” Social Thought and Policy Review, vol. 3, no. 2, pp. 1-23, 2025.
P. R. Choudhary, “Sentiment Analysis of Social Media Data for Public Opinion and Market Trend Prediction,” International Journal of Research Publications in Engineering, Technology and Management (IJR-PETM), vol. 8, no. 2, pp. 11768-11771, 2025, doi: 10.15662/IJRPETM.2025.0802002.
S. Swastiningsih, A. Aziz, and Y. Dharta, “The role of social media in shaping public opinion: a comparative analysis of traditional vs. digital media platforms,” The Journal of Academic Science, vol. 1, no. 6, pp. 620-626, 2024, doi: 10.59613/fm1dpm66.
M. Petrova and A. Tapsoba, “Information and conflict: From the role of (social) media and public opinion to big data and forecasting,” Economic Policy, vol. 40, no. 124, pp. 845-878, 2025, doi: 10.1093/epolic/eiaf012.
Z. Jiang, X. Li, S. Zhang, and X. Zhao, “A Weibo public opinion heat analysis and prediction model integrating BERT and X-means algorithms,” Computer Applications, vol. 45, no. 10, pp. 3138-3145, 2025, doi: 10.11772/j.issn.1001-9081.2024091371.
Y. Peng and M. Wang, “Automatic Content Generation and Public Opinion Analysis of Intelligent Agents in Social Networks,” Yangtze Information & Communication, vol. 38, no. 12, pp. 141-143+147, 2025.
D. Wang, F. Liu, and W. Lu, “Cross-Social Media Public Opinion Risk Perception: Construction and Implementation of a Theoretical Framework,” Journal of Information Science, vol. 43, no. 4, pp. 446-456, 2024, doi: 10.3772/j.issn.1000-0135.2024.04.006.
A. Bany Mohammed, M. Al-Okaily, D. Qasim, et al., “Digital activism and public opinion: understanding the role of social media during the Gaza Conflict,” Journal of Islamic Marketing, vol. 16, no. 11, pp. 3366-3393, 2025, doi: 10.1108/JIMA-03-2024-0101.
M. Hasanuddin, S. Khodijah, and C. A. Rizki, “Analysis of the Role of Social Media in Shaping Public Opinion on Social Issues,” Journal of Computer Science Artificial Intelligence and Communications, vol. 1, no. 1, pp. 7-11, 2024, doi: 10.64803/jocsaic.v1i1.1.
E. J. Hasibuan, A. D. R. Putra, and A. S. Dirgantari, “The role of social media algorithms in shaping public opinion during political campaigns,” International Journal of Social and Human, vol. 1, no. 2, pp. 165-172, 2024.
G. Alexander, “Role of social media influencers in shaping public opinion and consumer behavior in Greece,” International Journal of Communication and Public Relation, vol. 9, no. 1, pp. 13-26, 2024, doi: 10.47604/ijcpr.2269.
M. Reveilhac, S. Steinmetz, and D. Morselli, “A systematic literature review of how and whether social media data can complement traditional survey data to study public opinion,” Multimedia Tools and Applications, vol. 81, no. 7, pp. 10107-10142, 2022, doi: 10.1007/s11042-022-12101-0.
M. Zimmer and S. Logan, “Privacy concerns with using public data for suicide risk prediction algorithms: a public opinion survey of contextual appropriateness,” Journal of Information, Communication and Ethics in Society, vol. 20, no. 2, pp. 257-272, 2022, doi: 10.1108/JICES-08-2021-0086.
D. M. Houston and A. Barone, “How the engagement of high-profile partisan officials affects education politics, public opinion, and polarization,” Education Finance and Policy, vol. 21, no. 1, pp. 97-120, 2026, doi: 10.26300/gw47-cc09.
E. Holder and C. X. Bearfield, “Polarizing political polls: How visualization design choices can shape public opinion and increase political polarization,” IEEE Transactions on Visualization and Computer Graphics, vol. 30, no. 1, pp. 1446-1456, 2023, doi: 10.1109/TVCG.2023.3326512.
T. Manju, A. K. Tarofder, and F. Azam, “Does Gender Moderate the Mediating Effects of Public Opinion on Relationships Between Media Polarization and Voter Intention? A Simple Question and a Complex Answer,” Revista de Gestao Social e Ambiental, vol. 18, no. 6, pp. 1-34, 2024, doi: 10.24857/rgsa.v18n6-020.
S. Nasereddin, “Impact of social media platforms on international public opinion during the Israel war on Gaza,” Global Change, Peace & Security, vol. 35, no. 1, pp. 5-31, 2023, doi: 10.1080/14781158.2024.2415908.
A. Afyare and M. A. H. Orey, “The Influence of Social Media on Political Discourse and Public Opinion,” Architecture Image Studies, vol. 6, no. 3, pp. 1634-1667, 2025, doi: 10.62754/ais.v6i3.506.
Y. Sairambay, A. Kamza, Y. Kap, et al., “Monitoring public electoral sentiment through online comments in the news media: a comparative study of the 2019 and 2022 presidential elections in Kazakhstan,” Media Asia, vol. 51, no. 1, pp. 33-61, 2024, doi: 10.1080/01296612.2023.2229162.
D. Zhang, “Data mining and big data in social media public opinion monitoring,” Media and Communication Research, vol. 4, no. 10, pp. 44-51, 2023, doi: 10.23977/mediacr.2023.041007.
X. Chen, S. Duan, S. Li, et al., “A method of network public opinion prediction based on the model of grey forecasting and hybrid fuzzy neural network,” Neural Computing and Applications, vol. 35, no. 35, pp. 24681-24700, 2023, doi: 10.1007/s00521-023-08205-9.
J. Zhang and Z. Li, “Prediction and Guidance of Negative Public Opinion Dissemination Based on a Sentiment Classification Algorithm,” Journal of ICT Standardization, vol. 13, no. 3, pp. 243-256, 2025, doi: 10.13052/jicts2245-800X.1331.