Multi-Modal Machine Learning For Comprehensive Public Opinion Analysis In Diverse Regions

Dr. Zahra Al-Shehri; Prof. Faisal M. Al-Qahtani

Authors

Dr. Zahra Al-Shehri Center for Data Analytics and AI, King Saud University, Riyadh, Saudi Arabia
Prof. Faisal M. Al-Qahtani Artificial Intelligence and Data Analytics Research Center, King Abdulaziz University, Jeddah, Saudi Arabia

Keywords:

public opinion analysis, multi-modal machine learning, sentiment analysis, natural language processing

Abstract

Understanding public opinion is paramount for effective governance, social stability, and policy formulation, particularly in ethnically and culturally diverse regions. Traditional methods of gauging public sentiment often rely on limited data sources, primarily text, thereby overlooking crucial nuances conveyed through other modalities. This article proposes a novel multi-modal machine learning framework for the comprehensive monitoring and analysis of public opinion, specifically tailored for diverse regional contexts. The proposed system integrates natural language processing (NLP) for textual data, speech processing for audio inputs, and computer vision for visual content (images and videos). By leveraging deep learning techniques, the framework extracts topics, sentiments, and emotions across these diverse data streams. Fusion techniques are employed to combine insights from each modality, providing a more holistic and nuanced understanding of public discourse. The efficacy of this multi-modal approach is demonstrated through a conceptual framework highlighting its potential to overcome the limitations of uni-modal analysis, offering a richer context for policy-makers to understand community needs, identify emerging concerns, and foster social cohesion in complex, multi-ethnic environments.

References

Bashar, M.A., Nayak, R., Balasubramaniam, T., 2022. Deep learning based topic and sentiment analysis: COVID19 information seeking on social media. Social Network Analysis and Mining. 12 (1): 90. doi: 10.1007/s13278-022-00917-5.

Deng, W., Yang, Y., 2021. Cross-Platform Comparative Study of PublicConcern on Social Media during the COVID-19 Pandemic: An Empirical Study Based on Twitter and Weibo. International Journal of Environmental Research and Public Health. Jun 16; 18 (12):Pp. 6487. doi: 10.3390/ijerph18126487. PMID: 34208483; PMCID: PMC8296381.

Guo, Q., Pera, M. S., Wang, X., Zhang, X., Liu, Y., 2022. A Survey on Knowledge Graph-Based Recommender Systems. IEEE Transactions on Knowledge and Data Engineering, 34(8), Pp. 3549-3568. doi: 10.1109/TKDE.2020.3028705

Koehn, P., 2010. Statistical machine translation. Cambridge University Press.

Lalingkar, A., Audichya, V., Mishra, P., Mandyam, S., Srinivasa, S., 2022. Models for finding quality of affirmation and points of intervention in an academic discussion forum. Computers and Education: Artificial Intelligence, 3, 100046. https://doi.org/10.1016/j.caeai.2022.100046

Liu, L., Tang, L., Dong, W., Zhong, J., Yang, X., Zhang, H., 2016. An overview of topic modeling and its current applications in bioinformatics. SpringerPlus, 5, Pp. 1608. https://doi.org/10.1186/s40064-016-3252-8

Vidanaralage, A. J., Dharmaratne, A. T., Haque, S., 2022. AI-based multidisciplinary framework to assess the impact of gamified video-based learning through schema and emotion analysis. Computers and Education: Artificial Intelligence, 3, 100109. https://doi.org/10.1016/j.caeai.2022.100109

Xu, Q., Shen, Z., Shah, N., Cuomo, R., Cai, M., Brown, M, Li, J., Mackey, T., 2020. Characterizing Weibo Social Media Posts From Wuhan, China During the Early Stages of the COVID-19 Pandemic: Qualitative Content Analysis. JMIR Public Health Surveill. Dec 7; Pp. 6 (4): e24125. doi: 10.2196/24125.

Yao, L., Mimno, D., Mccallum, A., 2009. Efficient methods for topic model inference on streaming document collections. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Pp. 937-946.

Zeng, Q.T., Redd, D., Rindflesch, T.C., Nebeker, J.R., 2012. Synonym, topic model and predicate-based query expansion for retrieving clinical documents. AMIA 2012.

Zhang R, Cheng Z, Guan J, Zhou, S., 2015. Exploiting topic modeling to boost metagenomic reads binning. BMC Bioinformatics, 16(Suppl 5), Pp. 1-10.

Zhang, D., Lee, W. S., 2004. Automatic speech recognition: A deep learning approach. Springer.

Zhu, J., Ahmed, A., Xing E. P., 2012. MedLDA: maximum margin supervised topic models. Journal of Machine Learning Research, 13, Pp. 2237-2278.

Frontiers in Emerging Artificial Intelligence and Machine Learning

Article Details Page