Adapting Large Language Models for Topic Modeling Tasks
Open Access
- 17 November 2024
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 954-965
Abstract
This work presents a proposal for adapting Large Language Models (LLMs) to the unsupervised task of Topic Modeling (TM). Our proposal consists of three stages: document summarization, characterization of topics, and definition of topics. We instantiated our proposal with two LLMs, one open-source (Llama3) and the other proprietary (GPT 3.5), comparing them with four state-of-the-art (SOTA) strategies in TM. Our results demonstrated that the approach is very promising, having been able to define topics as coherent as SOTA strategies but still with room for improvement in terms of organizational structure.Keywords
This publication has 17 references indexed in Scilit:
- Semantic Academic Profiler (SAP): a framework for researcher assessment based on semantic topic modelingScientometrics, 2022
- A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospectsEngineering Applications of Artificial Intelligence, 2022
- Forty years of emergency medicine research: Uncovering research themes and trends through topic modelingThe American Journal of Emergency Medicine, 2021
- Machine learning in finance: A topic modeling approachEuropean Financial Management, 2021
- CluWords2019
- Semantically-Enhanced Topic Modeling2018
- A Feature-Oriented Sentiment Rating for Mobile App Reviews2018
- Probabilistic latent semantic indexing1999
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- A dendrite method for cluster analysisCommunications in Statistics, 1974