Sentiment Analysis for Thai dramas on Twitter

Pakawan Pugsee; Tanasit Rengsomboonsuk; Kawintida Saiyot

doi:10.14456/nujst.2022.2

Authors

Pakawan Pugsee Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.
Tanasit Rengsomboonsuk Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.
Kawintida Saiyot Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.

DOI:

https://doi.org/10.14456/nujst.2022.2

Keywords:

Sentiment analysis, Thai dramas, Naïve Bayes

Abstract

Since most consumers are interested in watching TV series and using online media such as Twitter to exchange opinions about them, there are a lot of comments are found and the consumers must take more time for reading and understanding the overall messages of the other consumers' views. Therefore, this research has studied about word grouping, classification of the sentiments of the text about Thai TV series called Thai dramas or Lakorn. The objective is to analyze the opinion messages expressed as like, dislike and neutral comments and the scope of this research is collecting texts about the dramas in Thai language, but it does not cover slang, misspellings, and dialects. Moreover, the implemented web application for analyzing opinions about Thai dramas on Twitter is developed to help analyzing and summarizing the preferences for Thai dramas. All words of collected Thai messages will be looked up in the vocabulary list created for the Thai dramas. Then, the word vectors of messages are generated for training a learning model using the Naïve Bayes approach. After that, the model will classify the comments about the dramas, whether most consumers like or not like the drama. The developed system is expected to be a tool that will be able to make decision watching the dramas easier and this will be beneficial to the drama producers to facilitate planning the production of the dramas in the future.

References

Baccianella, S., Esuli, A., & Sebastiani, F. (2010). Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. Proceedings of the 7th International Conference on Language Resources and Evaluation (pp. 2200-2204). Valletta, Malta: European Language Resources Association (ELRA). http://www.lrec-conf.org/proceedings/lrec2010/pdf/769_Paper.pdf

Chatchaithanawat, T., & Pugsee, P. (2015). A framework for laptop review analysis. Proceedings of the 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications. Chonburi, Thailand: IEEE. https://doi.org/10.1109/ICAICTA.2015.7335358

Deewattananon, B., & Sammapun, U. (2017). Analyzing user reviews in Thai language toward aspects in mobile applications. Proceedings of the 14th International Joint Conference on Computer Science and Software Engineering. Nakhon Si Thammarat, Thailand: IEEE. https://doi.org/10.1109/JCSSE.2017.8025903

Drus, Z., & Khalid, H. (2019). Sentiment Analysis in Social Media and Its Application: Systematic Literature Review. Procedia Computer Science, 161, 707–714. https://doi.org/10.1016/j.procs.2019.11.174

Lertsiwaporn, J., & Senivongse, T. (2017). Time-based visualization tool for topic modeling and sentiment analysis of Twitter messages. The International Multi Conference of Engineers and Computer Scientists.

Esuli, A. (2019). SentiWordNet 3.0: The sentiment lexicon [Data file]. Retrieved from https://github.com/aesuli/SentiWordNet

National Electronics and Computer Technology Center. (2020). LEXiTRON: Thai-English Electronic Dictionary. Retrieved from https://lexitron.nectec.or.th

Narayanan, V., Arora, I., & Bhatia, A. (2013). Fast and accurate sentiment classification using an enhanced Naive Bayes model, Lecture Notes in Computer Science (LNCS), 8206, 194-201. https://doi.org/10.1007/978-3-642-41278-3_24

Pasupa, K., & Seneewong Na Ayutthaya, T. (2019). Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features. Sustainable Cities and Society, 50, 101615.

Phatthiyaphaibun, W. (2017). Thai sentiment text [Data file]. Retrieved from https://github.com/PyThaiNLP/lexicon-thai/tree/master/ข้อความ

Piyaphakdeesakun, C., Facundes, N., & Polvichai, J. (2019). Thai comments sentiment analysis on social networks with deep learning approach. Proceedings of the 34th International Technical Conference on Circuits/Systems. Computers and Communications. https://doi.org/10.1109/ITC-CSCC.2019.8793324

Pugsee, P., & Chatchaithanawat, T. (2020). Opinion mining for laptop reviews using Naïve Bayes. Current Applied Science and Technology journal, 2(2), 278-294. https://li01.tci-thaijo.org/index.php/cast/article/view/240956/164396

Pugsee, P., Nussiri, V., & Kittirungruang, W. (2019). Opinion mining for skin care products on Twitter. Communications in Computer and Information Science (CCIS), 937, 261-271. https://doi.org/10.1007/978-981-13-3441-2_20

Pugsee, P., & Ongsirimongkol N. (2019). A classification model for Thai statement sentiments by deep learning techniques. Proceedings of the 2nd International Conference on Computational Intelligence and Intelligent Systems (pp. 22-27). The ACM International Conference Proceeding Series (ICPS). https://doi.org/10.1145/3372422.3372448

Pugsee, P., Sombatsri, P., & Juntiwakul, R. (2017). Satisfactory analysis for cosmetic product review comments. Proceedings of the 2017 International Conference on Data Mining, Communications, and Information Technology (pp. 1-6). The ACM International Conference Proceeding Series (ICPS). https://doi.org/10.1145/3089871.3089890

Python Software Foundation. (2020). PyThaiNLP: Python library for Thai natural language processing. Retrieved from https://pypi.org/project/pythainlp/

Python Software Foundation. (2020). Tweepy: Twitter library for Python. Retrieved from https://pypi.org/project/tweepy/

Scikit-learn Developers. (2020). Multinomial Naïve Bayes. Scikit-learn: Machine Learning in Python. Retrieved from https://scikit-learn.org/stable/modules/naive_bayes.html#multinomial-naive-bayes

Trakultaweekoon, K., & Klaithin, S. (2016). SenseTag: A tagging tool for constructing Thai sentiment lexicon Proceedings of the 13th International Joint Conference on Computer Science and Software Engineering. Khon Kaen, Thailand: IEEE. https://doi.org/10.1109/JCSSE.2016.7748868

Vateekul, P., & Koomsubha, T. (2016). A study of sentiment analysis using deep learning techniques on Thai Twitter data Proceedings of the 13th International Joint Conference on Computer Science and Software Engineering. Khon Kaen, Thailand: IEEE. https://doi.org/10.1109/JCSSE.2016.7748849