A Study of Sentiment Analysis based on Specific 6-emotion Category for Thai Language
Abstract
Social media such as Twitter, Facebook, Web logs and Review sites are indispensable tools for our customers’ communication sites. From a business perspective, it is important to improve customer satisfaction and customer insights by capturing and analyzing customer emotions in detail through social media, customer feedback from call centers, and questionnaire analysis. This paper presents an effective classification method for Thai. In order to solve the problem of linguistic difficulty in Thai, this method used sentiment analysis using 6-emotion as an aspect-based analysis method in addition to conventional sentiment analysis such as positive and negative. This paper describes the results of evaluating the usefulness of the 6-emotion analysis in helping to judge positive and negative in Thai sentences.
References
K. Takahashi, Doshisha University, Kyotanabe, Kyoto, Japan, ”Remarks on SVM-based emotion recognition from multi-modal bio-potential signals,” IEEE In-ternational Workshop on Robot and Human Communication (ROMAN), 22-22 Sept. 2004, DOI: 10.1109/ROMAN.2004.1374736
Udit Jain, Karan Nathani, Nersisson Ruban, Alex Noel Joseph Raj, Zhemin Zhuang, and Vijayalakshmi G.V. Mahesh, ”Cubic SVM Classifier Based Feature Extraction and Emotion Detection from Speech Signals,” 2018 International Conference on Sensor Networks and Signal Processing (SNSP), 28-31 Oct. 2018, DOI: 10.1109/SNSP.2018.00081
N. Sebe, M.S. Lew, I. Cohen; A. Garg, and T.S. Huang, ”Emotion recognition using a Cauchy Naive Bayes classifier,” 2002 International Conference on Pattern Recognition, 11-15 Aug. 2002, DOI: 10.1109/ICPR.2002.1044578
Sagar K. Bhakre; Arti Bang, ”Emotion recognition on the basis of audio signal using Naive Bayes classifier,” 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 21-24 Sept. 2016,DOI: 10.1109/ICACCI.2016.7732408
Peerapon Vateekul, ”A study of sentiment analysis using deep learning techniques on Thai Twitter data,” 2016 13th International Joint Conference on Computer Science and Software Engineering (JCSSE), https://ieeexplore.ieee.org/abstract/document/7748849
Pasupa, K., Seneewong Na Ayutthaya, T., ”Hybrid Deep Learning Models for Thai Sentiment Analysis,” Cogn Comput 14, 167–193 (2022). https://doi.org/10.1007/s12559-020-09770-0;
Ekman, P. (1972).,” Universals and Cultural Differences in Facial Expressions of Emotions,” In Cole, J. (Ed.), Nebraska Symposium on Motivation (pp. 207-282). Lincoln, NB: University of Nebraska Press.
Kunpattanasopon, N., Tongtep, N., and Hashimoto, K, ”Noise Reduction Effect on Thai Social Texts Sentiment Analysis,” The Joint International Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2017): 104-115, 2017.
Turney, P. D. ” Thumbs up or thumbs down? semantic orientation applied to un-supervised classification of reviews,” In: Proceedings of the 40th annual meeting on association for computational linguistics. 417-424, 2002
