The Technological Development and Application Frontiers of Social Media Sentiment Analysis: A Ten Year Review (2016-2026)
Main Article Content
Keywords
social media, emotional analysis, deep learning, large language model, multimodal fusion
Abstract
Social media sentiment analysis technology has been rapidly iterative in the past decade, but the existing research lacks a systematic review of its technology evolution and application context. This paper reviews the relevant literature from 2016 to 2026 from two dimensions of technology paradigm and application scenarios. The technical level has experienced four paradigm iterations from the explicit emotion classification of SVM and TextCNN, to the implicit emotion detection led by BiLSTM+Attention and BERT, to the multimodal fusion model, and to the generative reasoning of the big language model. The application level has been deeply embedded in public opinion governance, brand insight, financial forecasting and public health monitoring. The research points out that the lack of cross domain generalization, short text noise interference and model bias are the core bottlenecks. In the future, people should build a cross language unified model and a lightweight multimodal framework, and establish a fairness evaluation system.
References
- [1] Albladi, A., Islam, M., & Seals, C. (2025). Sentiment analysis of twitter data using NLP models: a comprehensive review. IEEE Access.
- [2] Rodríguez-Ibánez, M., Casánez-Ventura, A., Castejón-Mateos, F., & Cuenca-Jiménez, P. M. (2023). A review on sentiment analysis from social media platforms. Expert Systems with Applications, 223, 119862.
- [3] Rosenthal, S., Farra, N., & Nakov, P. (2017, August). SemEval-2017 task 4: Sentiment analysis in Twitter. In Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017) (pp. 502-518).
- [4] Li, Z., Zou, Y., Zhang, C., Zhang, Q., & Wei, Z. (2021, November). Learning implicit sentiment in aspect-based sentiment analysis with supervised contrastive pre-training. In Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 246-256).
- [5] Wei, J., Liao, J., Yang, Z., Wang, S., & Zhao, Q. (2020). BiLSTM with multi-polarity orthogonal attention for implicit sentiment analysis. Neurocomputing, 383, 165-173.
- [6] Ye, J., Zhou, J., Tian, J., Wang, R., Zhou, J., Gui, T., ... & Huang, X. (2022). Sentiment-aware multimodal pre-training for multimodal sentiment analysis. Knowledge-Based Systems, 258, 110021.
- [7] Liu, Z., Yang, K., Xie, Q., Zhang, T., & Ananiadou, S. (2024, August). Emollms: A series of emotional large language models and annotation tools for comprehensive affective analysis. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 5487-5496).
- [8] Smailova, A., Kuzembayeva, A., Utkelbay, R., Kukeyeva, F., & Baizakova, K. (2025). Public opinion monitoring technologies: how the state uses data to make political decisions. Frontiers in Political Science, 7, 1680172.
- [9] Boumhidi, A., Benlahbib, A., Cambria, E., & Nfaoui, E. H. (2025). Periodic insight: Multilingual reputation generation system through daily opinion mining analysis. Results in Engineering, 26, 104619.
- [10] Zhang, P., Harris, R. D., & Zheng, J. (2025). GNN-based social media sentiment analysis for stock market forecasting and trading. Expert Systems with Applications, 291, 128425.
- [11] Zhou, X., Zhang, X., Larson, H. J., de Figueiredo, A., Jit, M., Fodeh, S., ... & Hou, Z. (2023). Spatiotemporal trends in COVID-19 vaccine sentiments on a social media platform and correlations with reported vaccine coverage. Bulletin of the World Health Organization, 102(1), 32.
- [12] Wang, Z., Huang, D., Cui, J., Zhang, X., Ho, S. B., & Cambria, E. (2025). A review of Chinese sentiment analysis: subjects, methods, and trends. Artificial Intelligence Review, 58, 1.
- [13] Cui, J., Wang, Z., Ho, S. B., & Cambria, E. (2023). Survey on sentiment analysis: evolution of research methods and topics. Artificial intelligence review, 56(8), 8469-8510.
- [14] Jia, W., Shan, J., Wang, J., & Mengyang, Z. (2026). Implicit aspect-based sentiment analysis: A systematic review. ACM Computing Surveys, 58(10), 1-37.
- [15] Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial intelligence review, 55(7), 5731-5780.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.