<![CDATA[This study aims to analyze topics in YouTube comments related to online gambling using Latent Dirichlet Allocation (LDA) and BERTopic, as well as to compare the performance of both methods. The dataset consists of 6,350 YouTube comments obtained from Kaggle. The analysis process includes preprocessing, topic modeling, and evaluation using topic coherence and topic diversity metrics. The results show that LDA achieves a topic coherence score of 0.511 and a topic diversity score of 1.0, while BERTopic achieves a topic coherence score of 0.667 and a topic diversity score of 0.449. These findings indicate that BERTopic produces more semantically coherent topics compared to LDA, although it has a higher level of overlap between topics. Furthermore, the interpretation results reveal that several identified topics are related to online gambling promotion, while others are influenced by noise in the comment data. Therefore, BERTopic is considered more effective for analyzing short and unstructured text data.]]>
Copyrights © 2026
