Developing a sentiment classification model for Thai political tweets

Name: Pakawan Pugsee

Organization : Chulalongkorn University. Faculty of Science

Email : pakawan.p@chula.ac.th

Name: Jittiwat Jangjun

Organization : Chulalongkorn University. Faculty of Science

Email : jame.simplify@gmail.com

Name: Chonlawit Gonthong

Organization : Chulalongkorn University. Faculty of Science

Email : saguraisama@gmail.com

LCSH: Sentiment analysis

LCSH: Microblogs

LCSH: Communication in politics -- Thailand

LCSH: Thai language -- Data processing

LCSH: Machine learning

Abstract: This research focuses on the development and evaluation of sentiment classification models tailored to political discourse on social media. With the increasing volume of user-generated content, particularly on platforms such as X (formerly Twitter), it has become challenging to manually interpret political opinions expressed online. This study aims to classify Thai political tweets into three sentiment categories: positive, negative, and neutral, using advanced computational techniques. Thai-language political tweets were collected through keyword-based filtering and analyzed using a combination of natural language processing (NLP) methods, machine learning with logistic regression, and deep learning with long short-term memory (LSTM) neural networks. Two modeling approaches were compared in terms of sentiment classification performance. Experimental results indicate that the LSTM-based Universal Language Model Fine-Tuning (ULMFiT) approach outperforms logistic regression, achieving an accuracy and precision of approximately 70%, which is considered adequate for practical applications. Although the models demonstrate promising performance, further improvements are required to enhance classification accuracy, particularly in handling complex or ambiguous political expressions in Thai.

King Mongkut's University of Technology North Bangkok. Central Library

Address: BANGKOK

Email: library@kmutnb.ac.th

Created: 2025

Modified: 2026-02-24

Issued: 2026-02-24

บทความ/Article

application/pdf

BibliograpyCitation : In Prince of Songkla University, Phuket Campus. College of Computing. The 9th International Conference on Information Technology (InCIT 2025) (pp.138-145). Phuket : Prince of Songkla University

eng

©copyrights King Mongkut's University of Technology North Bangkok

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	InCIT 2025pp.138-145.pdf	506.21 KB

ใช้เวลา

0.031061 วินาที