<![CDATA[User review data on travel guidance services can be useful textual data for other users. By knowing what topics are discussed in user reviews in hotel products, travel guidance service providers can group these reviews based on the topics discussed. In grouping textual data into several topics, the use of topic modeling methods can be done. In this study, the author uses the BERTopic method in modeling topics on user review data related to hotel products on one of the TripAdvisor travel guidance services. This study uses secondary data in the form of hotel reviews on the TripAdvisor site. Topic modeling with BERTopic begins with document embedding, dimensionality reduction (UMAP), clustering (HDBSCAN), and c-TF-IDF. Topic modeling using the BERTopic method resulted in 78 topics with a topic coherence value of 0.07287 and a topic diversity of 0.496154. The lower the number of topics to be generated, the value of topic coherence and topic diversity decreases]]>
Copyrights © 2022
