Enhancing Efficiency of Thai Opinions Models on Artificial Intelligence using Word Segmentation Techniques
Article Sidebar
Main Article Content
Abstract
This research aimed to analyze word segmentation techniques that improve the performance of sentiment classification models for Thai people’s opinions toward artificial intelligence. The data were collected from social media platforms, consisting of 8,091 comments. The researcher selected only comments containing more than 10 words for analysis, resulting in a total of 1,767 comments. In the text mining process, word segmentation is an important and time-consuming step. Therefore, the researcher employed Newmm, Deepcut, Longest, and Attacut techniques for word segmentation. For model construction, Naive Bayes, Support Vector Machine, K-Nearest Neighbors, and C4.5 Decision Tree techniques were applied, as these techniques are reliable, widely accepted, and commonly used in research studies. The performance evaluation employed the 10-Fold Cross Validation method for data partitioning. The effectiveness of the word segmentation techniques was measured using Accuracy, Precision, Recall, and F1-Score. The experimental results revealed that the Deepcut technique, which is a data-driven word segmentation approach, could effectively handle comments containing new or informal words. When combined with the Support Vector Machine technique, which performs well with high-dimensional and complex data containing formal words, informal expressions, and newly emerging terms, the combination achieved the best performance. The results yielded an accuracy of 93.42 %, a recall of 97.03 %, and an F1-score of 94.54 %.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Aasim, M., Katırcı, R., Acar, A.Ş. and Ali, S.A. (2024). A Comparative and Practical Approach Using Quantum Machine Learning (QML) and Support Vector Classifier (SVC) for Light Emitting Diodes Mediated In Vitro Micropropagation of Black Mulberry (Morus nigra L.). Industrial Crops and Products, 213. https://doi.org/10.1016/j.indcrop.2024.118397
Aha, D.W., Kibler, D. and Albert, M.K. (1991). Instance-Based Learning Algorithms. Machine Learning, 6, 37-66. https://doi.org/10.1007/BF00153759
Aprilianti, H., Mustofa, H., Umam, K. and Handayani, M.R. (2025). Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews. Journal of Applied Informatics and Computing, 9(3), 920-927. https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9482
Bowornlertsutee, P. and Paireekreng, W. (2022). Sentiment Analysis Techniques of Online Product Reviews. Recent Science and Technology, 14(3), 755-769. https://li01.tci-thaijo.org/index.php/rmutsvrj/article/view/245470
Chang, C.C. and Lin, C.J. (2011). LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology, 2(3), 1-27. https://doi.org/10.1145/1961189.1961199
Chantanapelin, S., Keatchalermkun, S., Srivichai, M. and Srichai, P. (2024). Marketing Strategies for Developing and Managing Tourist Attractions Post-Covid 19 Pandemic: a Market Research Review Through Sentiment Analysis of Online Media Via Chat GPT Mechanism Case Study: Chiang Rai Night Bazaar Tourism Market. Journal of Management and Marketing, 11(2), 24-39. https://so05.tci-thaijo.org/index.php/mmr/article/view/269115
Charmanas, K., Georgiou, K., Papageorgiadis, K., Mittas, N. and Angelis, L. (2026). A Topic-Oriented Trend Analysis Framework for Stack Exchange Questions: Case Study on ChatGPT Related Queries on Stack Overflow. Information and Software Technology, 190. https://doi.org/10.1016/j.infsof.2025.107969
Damrongkamoltip, K., Ruenlek, K., Limprasert, W. and Boonkwan, P. (2024). Comparing a Thai Words Segmentation Methods in the LST20 Dataset. Journal of Computer and Creative Technology, 2(2), 61-70. https://so13.tci-thaijo.org/index.php/jcct/article/view/679
Demir, N.Y. and Egbert, J. (2026). Register Alignment of ChatGPT-Generated Academic Texts. Applied Corpus Linguistics, 6(1). https://doi.org/10.1016/j.acorp.2025.100174
Duangtham, S., Lertritrungrot, S., Hongboonmee, N. and Massagram, W. (2025). Leveraging PyThaiNLP for Sentiment Analysis of Thai Online Text: A Comparative Study of Logistic Regression and Support Vector Machine. Journal of Applied Informatics and Technology, 7(2), 268-282. https://ph01.tci-thaijo.org/index.php/jait/article/view/256625
Handayani, H., Novita, R., Permana, I. and Megawati. (2024). Sentiment Analysis of X Users on Iconnet Service Provider Using Naïve Bayes and Support Vector Machine. Proceedings of the 2024 IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS), 1-6. https://doi.org/10.1109/AIMS61812.2024.10512562
Iakovidis, I. and Bozzeda, F. (2025). Applications of Machine Learning Algorithms to a Sandy Beaches Ecological Database: an Empirical and Critical Comparison. Estuarine Coastal and Shelf Science, 326. https://doi.org/10.1016/j.ecss.2025.109539
John, G.H. and Langley, P. (1995). Estimating Continuous Distributions in Bayesian Classifiers. In P. Besnard & S. Hanks (Eds.), Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (pp. 338-345). Morgan Kaufmann.
Kaya, A. and Yildiz, G.N. (2026). The Evolution of Publications on Applications of Artificial Intelligence to Nursing Care: A Bibliometric and Visual Mapping Approach. Nursing Outlook, 74(1). https://doi.org/10.1016/j.outlook.2025.102609
Khunsuk, T. and Thongkam, J. (2020). Feature Selection Method for Improving Customer Reviews Classification. RMUTI JOURNAL Science and Technology, 13(1), 129-143. https://ph01.tci-thaijo.org/index.php/rmutijo/article/view/188091
Laosen, N., Laosen, K. and Paklao, T. (2024). Named Entity Recognition for Thai Historical Data. In 2024 21st International Joint Conference on Computer Science and Software Engineering (JCSSE) (pp. 528-533). IEEE. https://doi.org/10.1109/JCSSE61278.2024.10613644
Laowsungsuk, P., Jinda, A. and Sitthisarn, S. (2017). Sentiment Analysis of Restaurant Reviews on Review Web Sites. Thaksin University Journal, 20(1), 39-47. https://ph02.tci-thaijo.org/index.php/tsujournal/article/view/90081
Maisook, P. and Thongkam, J. (2025). Classifying Thai Social Media Opinions in the Covid Vaccine Using Text Mining. Journal of Science and Technology Buriram Rajabhat University, 9(1), 17-30. https://ph02.tci-thaijo.org/index.php/scibru/article/view/256167
Malakouti, S.M., Menhaj, M.B. and Suratgar, A.A. (2023). The Usage of 10-Fold Cross-Validation and Grid Search to Enhance ML Methods Performance in Solar Farm Power Generation Prediction. Cleaner Engineering and Technology, 15. https://doi.org/10.1016/j.clet.2023.100664
Manhem, M., Dolah, S., Chunkaew, S. and Mak-on, S. (2020). Model for the Classification of Feelings of Reviews Using Techniques Decision Trees Case Studies Hotel Reservation Web Site. Journal of Science and Technology, Songkhla Rajabhat University, 1(2), 69-79. https://ph02.tci-thaijo.org/index.php/SciAndTechSkru/article/view/244056
Md Suhaimin, M.S., Ahmad Hijazi, M.H., Moung, E.G., Nohuddin, P.N.E., Chua, S. and Coenen, F. (2023). Social Media Sentiment Analysis and Opinion Mining in Public Security: Taxonomy, Trend Analysis, Issues and Future Directions. Journal of King Saud University - Computer and Information Sciences, 35(9). https://doi.org/10.1016/j.jksuci.2023.101776
Methachaloemphat, R. (2022, 19 August). Applying Machine Learning to Industrial Applications (Part 1). https://www.nectec.or.th/news/news-public-document/machine-learning-manufact-1.html
Mohammadi, M., Dawodi, M., Wada, T. and Ahmadi, N. (2019). Comparative Study of Supervised Learning Algorithms for Student Performance Prediction. In 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (pp. 124-127). IEEE. https://doi.org/10.1109/ICAIIC.2019.8669085
Naiyjit, K. (2023, 9 March). Evaluation Metrics for Deep Learning Models. Kittimasak. https://kittimasak.com/evaluation-metrics-deep-learning/
Noonpakdee, W., Oranop na Ayutthaya, C. and Yuwakosol, S. (2023). Lexicon Construction for Sentiment Analysis in Media Quality Rating. Journal of Roi Kaensarn Academi, 8(5), 512-526. https://so02.tci-thaijo.org/index.php/JRKSA/article/view/261233
Phaewattanakul, K. and Luenam, P. (2014). Opinion Mining from Online Social Networks. Modern Management Frontier Journal, 11(2), 11-20. https://so04.tci-thaijo.org/index.php/stou-sms-pr/article/view/16934
Phatthiyaphaibun, W., Chaovavanich, K., Polpanumas, C., Suriyawongkul, A., Lowphansirikul, L. and Chormai, P. (2020, 17 July). PyThaiNLP. Github. https://github.com/PyThaiNLP/pythainlp/blob/dev/README_TH.md
Phatthiyaphaibun, W., Chaovavanich, K., Polpanumas, C., Suriyawongkul, A., Lowphansirikul, L., Chormai, P., Limkonchotiwat, P., Suntorntip, T. and Udomcharoenchaikit, C. (2023). PyThaiNLP: Thai natural language processing in Python. In Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023) (pp. 25-36). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.nlposs-1.4
Prakash, A. and Poulose, A. (2025). Electroencephalogram-Based Emotion Recognition: a Comparative Analysis of Supervised Machine Learning Algorithms. Data Science and Management, 8(3), 342-360. https://doi.org/10.1016/j.dsm.2024.12.004
PyThaiNLP. (2024, 16 May). Pythainlp Tokenize. Pythainlp. https://pythainlp.org/docs/5.0/api/tokenize.html
Ray, S. (2019). A Quick Review of Machine Learning Algorithms. In 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon) (pp. 35-39). IEEE. https://doi.org/10.1109/COMITCon.2019.8862451
Rodríguez, D.M., Cuéllar, M.P. and Morales, D.P. (2024). On the Fusion of Soft-Decision-Trees and Concept-Based Models. Applied Soft Computing, 160. https://doi.org/10.1016/j.asoc.2024.111632
Roudak, M.A., Farahani, M. and Hosseinbeigi, F.B. (2024). Extension of K-Nearest Neighbors and Introduction of an Applicable Prediction Criterion for a Novel Monte Carlo Simulation-Based Method in Structural Reliability. Structures, 66. https://doi.org/10.1016/j.istruc.2024.106867
Sadia, A., Khan, F. and Bashir, F. (2018). An Overview of Lexicon-Based Approach For Sentiment Analysis. In 2018 3rd International Electrical Engineering Conference (IEEC 2018). https://ieec.neduet.edu.pk/2018/Papers_2018/15.pdf
Sancoko, S.D., Diwandari, S. and Fachrie, M. (2022). Ensemble Learning for Sentiment Analysis on Twitter Data Related to Covid-19 Preventions. In Proceedings of the 2022 International Conference on Information Technology Research and Innovation (ICITRI) (pp. 89-94). IEEE. https://doi.org/10.1109/ICITRI56423.2022.9970234
Seeha, S., Bilan, I., Mamani Sanchez, L., Huber, J., Matuschek, M. and Schütze, H. (2020). ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation. In Proceedings of the Twelfth Language Resources and Evaluation Conference, (pp. 6947-6957). European Language Resources Associationhttps://aclanthology.org/2020.lrec-1.858/
Shang, Y. (2024). Prevention and Detection of DDOS Attack in Virtual Cloud Computing Environment Using Naive Bayes Algorithm of Machine Learning. Measurement: Sensors, 31. https://doi.org/10.1016/j.measen.2023.100991
Sheth, V., Tripathi, U. and Sharma, A. (2022). A Comparative Analysis of Machine Learning Algorithms for Classification Purpose. Procedia Computer Science, 215, 422-431. https://doi.org/10.1016/j.procs.2022.12.044
Soisoonthorn, T., Unger, H. and Maliyaem, M. (2023). Thai Word Segmentation with a Brain-Inspired Sparse Distributed Representations Learning Memory. Computational Intelligence and Neuroscience, 2023. https://doi.org/10.1155/2023/8592214
Soontranon, N. (2024, 24 April). K-Fold Cross Validation. Nerd. https://www.nerd-data.com/k-folds-cross-validation/
Turmuzi, M., Azmi, S. and Kertiyani, N.M.I. (2026). ChatGPT in School Mathematics Education: A Systematic Review of Opportunities, Challenges, and Pedagogical Implications. Teaching and Teacher Education, 170. https://doi.org/10.1016/j.tate.2025.105286
