Topic Modeling Enhancement using Summaries Generated by LLM Models

Designing effective topic models for long and unstructured documents is essential for detecting significant topics within them. However, traditional topic modeling approaches have certain drawbacks, such as the presence of overlapping topics and difficulties in processing long documents. This research investigates the potential of large language models (LLMs) to enhance the uncovering of underlying topics within these documents. This paper compares two methods of using the BERTopic model. The first method segments the documents into paragraphs and classifies them using BERTopic, and the second method involves an LLM dividing documents into token segments and summarizing them. These summaries are then classified into coherent topics using the BERTopic model. The results show that summarizing the documents and then classifying them using BERTopic yields better performance values compared to segmenting the documents into paragraphs and then classifying them using BERTopic.