Development of Sentiment Analysis Model Based on Thai Social Media Using Deep Learning Techniques
Keywords:
Long Short-Term Memory, Gated Recurrent Unit, Sentiment analysis, Deep Learning Convolutional, Convolutional Neural NetworkAbstract
This research purpose is a sentiment analysis model based on Thai social media using deep learning techniques consisting of Convolutional Neural networks, Long Short-Term Memory, and Gated Recurrent units. This research was tested with a wongnai product and service opinion dataset and measured its effectiveness based on Accuracy. The experiment of this research found Long Short-Term Memory provides better classification accuracy than Convolutional Neural networks and Gated Recurrent units with an accuracy of 83.7%, followed by Convolutional Neural networks with an accuracy of 77.0%, Finally Gated Recurrent units with an accuracy of 65.4% respectively. Therefore, it can be concluded that the Long Short-Term Memory model is the most appropriate and effective for creating an automated sentiment analysis system. The reason is that this algorithm takes into account the context of Thai words and is designed for sequential processing as well as its internal memory.
References
Sharma D, Sabharwal M, Goyal V, Vij M. Sentiment Analysis Techniques for Social Media Data: A Review. In: proceedings of the First International Conference on Sustainable Technologies for Computational Intelligence. Advances in Intelligent Systems and Computing: Vol. 1045. Singapore: Springer; January 2020. p.75-90.
Ahmad R, Shaikh Y. Opinion Mining and Sentiment Analysis for Classification of Opinions on Social Networking Sites Using Machine Learning Algorithms: Systematic Literature Review. Int j adv res comput commun eng 2021;10(5):488-94.
Wongnai. [Internet].2022 [cited 2022 June 30]. Available from: https://www.wongnai.com/businesses?domain=1
Tesmuang R, Chirawichitchai N. Thai Sentiment Analysis of Product Review Online Using Genetic Algorithms with Support Vector Machine. J Appl Sci Adv Technol 2020;10(2):7-13.
Tesmuang R, Chirawichitchai N. Thai Sentiment Analysis of Product Review Online Using Support Vector Machine. EJSU 2017;18(1):1-12.
Chirawichitchai N. Emotion classification of Thai text based using term weighting and machine learning techniques. In: proceedings of the 11th International Joint Conference on Computer Science and Software Engineering. Thailand: IEEE; May 2014. p.91-96.
Tesmuang R, Chirawichitchai N. Thai Sentiment Analysis of Product Review Online Using Genetic Algorithms with Support Vector Machine. J Appl Sci Adv Technol 2020;10(2):7-13.
Saihan L, Gong B. Word embedding and text classification based on deep learning methods. In: proceedings of the MATEC Web of Conferences: Vol. 336. China: EDP Sciences; January 2021. p.1-5.
Kalchbrenner N, Grefenstette E, Blunsom P. A Convolutional Neural Network for Modelling Sentences. In: Proceedings of the 52th Annual Meeting of the Association for Computational Linguistics. Maryland: Association for Computational Linguistics; June 2014. p.655–65.
Xingjian S, Zhourong C, Wang H, Yeung D, Wong K, Wang W. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In: proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems. Canada: MIT Press; December 2015. p.802-10.
Tensorflow 2.0 Keras - LSTM vs GRU Hidden States. [Internet].2022 [cited 2022 June 20]. Available from: https://tiewkh.github.io/blog/gru-hidden-state/
Chung J, Gulcehre C, Cho K, Bengio Y. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. In: proceedings of the 28th Conference on Neural Information Processing Systems. CANADA: MIT Press; December 2014. p.1-9.
Chirawichitchai N. Sentiment classification by a hybrid method of greedy search and multinomial naïve bayes algorithm. In: proceedings of the 8th international conference on ICT and knowledge engineering. Thailand: IEEE; November 2013. p.1-4.
Murthy N, Allu S, Andhavarapu B, Bagadi M, Belusonti M. Text based Sentiment Analysis using LSTM. Int J Eng Res Technol 2020;9(05):299-303.
Kurniasari L, Setyanto A. Sentiment Analysis Using Recurrent Neural Network-LSTM In Bahasa Indonesia. Eng Sci Technol an Int J 2020;15(5):3242-56.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Huachiew Chalermprakiet Science and Technology Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
บทความทุกบทความที่ได้รับการตีพิมพ์ถือเป็นลิขสิทธิ์ของ คณะวิทยาศาสตร์แฟละเทคโนโลยี มหาวิทยาลัยหัวเฉียวเฉลิมพระเกียรติ
