Types of Thai words Affecting the Effectiveness of Opinion Classification Models: Case Study of Thai People's Opinions on COVID-19
Article Sidebar
Main Article Content
Abstract
The purpose of this research is to study the effect of types of Thai words on the effectiveness of opinion classification models used for Thai people's opinions on COVID-19 from social media. The sentiments about COVID-19 in Thai language were collected from Twitter and Pantip websites up to 2,920 sentiments. The text mining processes were utilized to extract the data into 2 data sets including adverbs and verbs that indicated whether the data were positive or negative opinions. Furthermore, this research also added one more set of data containing both adverbs and verbs. Therefore, there were total of 3 data sets containing only adverbs, only verbs and both adverbs and verbs for examining the effect of types of Thai words on the effectiveness of the opinion classification models. In this research, 5 techniques were used to build the models including Decision Tree C4.5 (C4.5), Naive Bayes (NB), K-Nearest Neighbor (KNN), Multi-layer Perceptron (MLP) and Deep learning (DL). To evaluate effectiveness of the models, the 10-fold cross validation was used as the evaluation method and F-Measure, precision, recall and Matthews correlation coefficient were used as evaluation criteria. The results demonstrated that technique MLP had the highest effectiveness scores of 100% for all of the criteria when using the data set containing only adverbs and technique KNN had the highest effectiveness scores of 100% for all of the criteria when using the data set containing only adverbs and verbs. This research indicated that types of Thai words affected the effectiveness of opinion classification models.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
บทความที่ได้รับการตีพิมพ์เป็นลิขสิทธิ์ของ วารสารวิทยาศาสตร์และเทคโนโลยี มหาวิทยาลัยอุบลราชธานี
ข้อความที่ปรากฏในบทความแต่ละเรื่องในวารสารวิชาการเล่มนี้เป็นความคิดเห็นส่วนตัวของผู้เขียนแต่ละท่านไม่เกี่ยวข้องกับมหาวิทยาลัยอุบลราชธานี และคณาจารย์ท่านอื่นๆในมหาวิทยาลัยฯ แต่อย่างใด ความรับผิดชอบองค์ประกอบทั้งหมดของบทความแต่ละเรื่องเป็นของผู้เขียนแต่ละท่าน หากมีความผิดพลาดใดๆ ผู้เขียนแต่ละท่านจะรับผิดชอบบทความของตนเองแต่ผู้เดียว
References
Agarwal, V. and Sunitha, B.K. 2020. COVID-19 current pandemic and its societal impact. International Journal of Advanced Science and Technology. 29: 432-439.
Phumkhachorn, P. and Rattanachaikunsopon, P. 2020. Coronaviruses: Biological diasters from SARS and MERS to COVID-19. Journal of Science and Technology, Mahasarakham University. 39(6): 598-604. (in Thai)
Malik, M. and et al. 2018. A novel approach to web-based review analysis using opinion mining. Procedia Computer Science. 132: 1202-1209.
Somjettana, S. and Thongkam, J. 2021. Performance comparison of data mining techniques for building classification models of the Parent toward children who use smart phone. Journal of Science and Technology, Ubon Ratchathani University. 23(1): 21-30. (in Thai)
Phosaard, S. and Posawang, P. 2019. Classification for bus driver’s behaviors using text extraction and machine learning technique. Information Technology Journal. 15(1): 71-80. (in Thai)
Khunsuk, T. and Thongkam, J. 2020. Feature selection method for improving customer reviews classification, RMUTI Journal Science and Technology. 13(1): 129-143. (in Thai)
Supianto, A.A. and et al. 2018. Decision tree usage for student graduation classification: A comparative case study in Faculty of Computer Science Brawijaya University. In: Proceedings of the 2018 International Conference on Sustainable Information Engineering and Technology (SIET), 10-12 November 2018. Malang, Indonesia.
Chen, Y. and et al. 2017. A convolutional neural network for traffic information sensing from social media text. In: Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 16-19 October 2017. Yokohama, Japan.
Suksangaram, W. and et al. 2018. Predicting learning organization factors that affect performance by data mining techniques. In: Proceedings of the 2018 International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), 15-17 November 2018. Pattaya, Thailand.
Pinmuang, N. and Thongkam, J. 2018. Classifying Thai opinions on online media using text mining. Journal of Science and Technology, Mahasarakham University. 37(3): 372-379. (in Thai)
Gupta, S. and et al. 2018. Opinion mining for hotel rating through reviews using decision tree classification method. International Journal of Advanced Research in Computer Science. 9(2): 180-184.
Thongkam, J. and Khunsuk, T. 2021. Translate Thai subtitles at anonymous. Journal of Industrial Technology, Ubon Ratchathani Rajabhat University. 11(1): 83-94. (in Thai)
Watchareewan, J. and Sunantha, S. 2017. Text classifcation analysis by stability comparison of algorithms. Sripatum Review of Science and Technology. 9(1): 19-31. (in Thai)
Hossain, T. and et al. 2017. Machine learning based class level prediction of restaurant reviews. In: Proceedings of the 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), 21-23 Dec 2017. Dhaka, Bangladesh.
Xu, X. and et al. 2020. Application of neural network algorithm in fault diagnosis of mechanical intelligence. Mechanical Systems and Signal Processing. 141: 1-13.
