Large Language Model and Formal Concept Analysis: a comparative study for Topic Modeling

TL;DR

This paper compares Large Language Models and Formal Concept Analysis for topic modeling, evaluating their effectiveness and differences through experiments on teaching materials and research articles.

Contribution

It provides a comparative analysis of LLM and FCA in topic modeling, highlighting their respective strengths and weaknesses in practical applications.

Findings

FCA effectively visualizes topics using the CREA pipeline.

GPT-5 successfully generates and labels topics in a zero-shot setup.

Both methods show complementary strengths in topic extraction.

Abstract

Topic modeling is a research field finding increasing applications: historically from document retrieving, to sentiment analysis and text summarization. Large Language Models (LLM) are currently a major trend in text processing, but few works study their usefulness for this task. Formal Concept Analysis (FCA) has recently been presented as a candidate for topic modeling, but no real applied case study has been conducted. In this work, we compare LLM and FCA to better understand their strengths and weakneses in the topic modeling field. FCA is evaluated through the CREA pipeline used in past experiments on topic modeling and visualization, whereas GPT-5 is used for the LLM. A strategy based on three prompts is applied with GPT-5 in a zero-shot setup: topic generation from document batches, merging of batch results into final topics, and topic labeling. A first experiment reuses the teaching materials previously used to evaluate CREA, while a second experiment analyzes 40 research articles in information systems to compare the extracted topics with the underling subfields.