Design of a Multimodal Intelligent Public Opinion Analysis System

DOI: https://doi.org/10.62517/jbdc.202501111

Author(s)

Xinyu Long*, Jiaqing Huang, Yinying Li, Peng Ai, Yang Zhang

Affiliation(s)

College of Electrical Engineering, Southwest Minzu University, Chengdu, China

Abstract

As an emerging research field, multimodal sentiment analysis tasks aim to identify the speaker's emotions by combining information from different modalities. In recent years, it has been increasingly used in areas such as public opinion analysis, intelligent dialogue and user profiling. This article systematically sorts out the development context of multimodal intelligent public opinion analysis technology, and focuses on the application status of minority language processing technology in the field of public opinion monitoring. By analyzing the technical bottlenecks of the current public opinion analysis system, a multimodal fusion solution based on deep learning is proposed, and the effectiveness of the solution in social governance in ethnic minority areas is verified by combining actual cases. The research results show that a multimodal system integrating speech recognition, machine translation and sentiment analysis can significantly improve the efficiency of processing public opinion in minority languages and provide technical support for maintaining social stability in ethnic regions.

Keywords

Multimodal Analysis; Deep Learning; Public Opinion Analysis; Machine Translation; Sentiment Analysis

References

[1]Sun Hongkai, Huang Xing. Special topic research: Language identification. Language Strategy Research, 2018, (2):5-5. [2]Deng L, Yu D. Deep leaning: Methods and applications. Foundations and Sipnal Processing, 2014, 7(3-4):197-387 [3]Liu Z, Zhang L, Tu CC, et al. Statistical and semantic analysis of rumors in Chinese social media. Scientia Sinica Informationis, 2015, 45(12):1536-1546. [4]Bian T, Xiao X, Xu T, et al. Rumor detection on social media with bi-directional graph convolutional networks//Proceedings of the AAAI Conference on Artificial Intelligence.2020, 34(01):549-556. [5]Maimaiti Ayifu, Wushouer, Paridan, Yang Wenzhong. Uyghur named entity recognition based on Bi LSTM-CNN-CRF model. Computer Engineering, 2018, 44(08):230-236. [6]Chiu JPC, Nichols E. Named Entity Recognition with Bidirectional LSTM-CNNs. Computer Science, 2015. [7]Yadav V, Bethard S. A Survey on Recent Advances in Named Entity Recognition from Deep Learning models//Proceedings of the 27th International Conference on Computational Linguistics. 2018, 2145-2158. [8]Taboada M, Brooke J, Tofiloski M, et al. Lexicon-Based Methods for Sentiment Analysis. Computational Linguistics, 2011, 37(2):267-307. [9]Ma Y, Peng H, Khan T, et al. Sentic LSTM: a hybrid network for targeted aspect-based sentiment analysis. Cognitive Computation, 2018, 10(4):639-650. [10]Hyun D, Park C, Yang M C, et al. Target-aware convolutional neural network for target-level sentiment analysis. Information Sciences, 2019, 491:166-178. [11]Qin Y, Wang Z, Zhou W, et al. Learning from explanations with neural module execution tree//International Conference on Learning Representations. 2020. [12]Kuo Zunwang. Research on Several Key Theories and Applications of Network Public Opinion Analysis. Xinjiang University, 2021. [13]Shutova E, Kiela D, Maillard J. Black holes and white rabbits: Metaphor identification with visual features//Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Human language technologies. 2016, 160-170. [14]Morvant E, Habrard A, Ayache S. Majority vote of diverse classifiers for late fusion//Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, S+ SSPR 2014, Joensuu, Finland, August 20-22, 2014. Proceedings. Springer Berlin Heidelberg, 2014, 153-162. [15]Evangelopoulos G, Zlatintsi A, Potamianos A, et al. Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention. IEEE Transactions on Multimedia, 2013, 15(7):1553-1568 [16]Wadawadagi R, Pagi V. Sentiment analysis with deep neural networks: comparative study and performance assessment. Artificial Intelligence Review, 2020, 53(8):6155-6195. [17]Dharaniya R, Indumathi J, Uma G V. Automatic scene generation using sentiment analysis and bidirectional recurrent neural network with multi-head attention. Neural Computing and Applications, 2022, 34(19):16945-16958. [18]Swathi T, Kasiviswanath N, Rao A A. An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis. Applied Intelligence, 2022, 52(12):13675-13688. [19]Sun K, Shi X, Gao H, et al. Incorporating Pre-trained Transformer Models into TextCNN for Sentiment Analysis on Software Engineering Texts//Proceedings of the 13th Asia-Pacific Symposium on Internetware. 2022, 127-136. [20]Wu H, Zhang Z, Shi S, et al. Phrase dependency relational graph attention network for Aspect-based Sentiment Analysis. Knowledge-Based Systems, 2022, 236:107736.