@article{ART003212321},
author={Ika Widiastuti and Hwanseung Yong},
title={A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2025},
volume={21},
number={2},
pages={131-143}
TY - JOUR
AU - Ika Widiastuti
AU - Hwanseung Yong
TI - A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data
JO - Journal of Software Assessment and Valuation
PY - 2025
VL - 21
IS - 2
PB - Korea Software Assessment and Valuation Society
SP - 131
EP - 143
SN - 2092-8114
AB - Identifying coherent topics from social media data is challenging due to its informal style, short length, and high noise levels. Additionally, manually processing such data to extract useful information is both time-consuming and resource-intensive given the massive volume of user-generated content online. To address these challenges, this study evaluates the effectiveness of a previously proposed topic refinement method applied to social media data, including YouTube comments and Twitter posts. Prior to analysis, the datasets underwent preprocessing steps involving the removal of spam comments, offensive content, and short or non-informative comments. The refinement method was then applied post-topic extraction to identify and replace misaligned words using GPT and coherence filtering. The experimental results indicate that the method consistently improves coherence scores across all models and both domains, demonstrating its effectiveness and generalizability in enhancing topic quality in real-world social media discourse
KW - Topic Modeling;Topic Refinement;Topic Coherence;GPT;Coherence Filtering;Social Media Data
DO -
UR -
ER -
Ika Widiastuti and Hwanseung Yong. (2025). A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data. Journal of Software Assessment and Valuation, 21(2), 131-143.
Ika Widiastuti and Hwanseung Yong. 2025, "A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data", Journal of Software Assessment and Valuation, vol.21, no.2 pp.131-143.
Ika Widiastuti, Hwanseung Yong "A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data" Journal of Software Assessment and Valuation 21.2 pp.131-143 (2025) : 131.
Ika Widiastuti, Hwanseung Yong. A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data. 2025; 21(2), 131-143.
Ika Widiastuti and Hwanseung Yong. "A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data" Journal of Software Assessment and Valuation 21, no.2 (2025) : 131-143.
Ika Widiastuti; Hwanseung Yong. A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data. Journal of Software Assessment and Valuation, 21(2), 131-143.
Ika Widiastuti; Hwanseung Yong. A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data. Journal of Software Assessment and Valuation. 2025; 21(2) 131-143.
Ika Widiastuti, Hwanseung Yong. A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data. 2025; 21(2), 131-143.
Ika Widiastuti and Hwanseung Yong. "A Topic Refinement Framework Using GPT and Coherence Filtering to Enhance Topic Coherence in Social Media Data" Journal of Software Assessment and Valuation 21, no.2 (2025) : 131-143.
