Abstract
This project aims to use Topic Modeling on Customer Feedback from an Online Ticketing System using Latent Dirichlet Allocation and BERTopic. The experiment started with analysis of the Topics generated from a base LDA model and computing its coherence score and fine-tuning the LDA model and comparing the coherence score with the base Model. It was found that the fine-tuned LDA model increased the cohesion score by 8.33%. This project also explored the use of BERTopic, using the multilingual model and found that it was able to extract Tagalog words from the data composed of English and Tagalog. As such, BERTopic can be further experimented on using data with more relevant Tagalog words. Also, using human judgements or “eye-balling” techniques, it was able to evaluate that the topic distribution generated by both the LDA and BERTopic model was able to capture the information needed by the organization.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
