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

2026-02-02

AI Summary

This study systematically compares the performance of large language models (LLMs) and Formal Concept Analysis (FCA) in topic modeling, addressing a gap in empirical research on LLMs for this task. Focusing on two datasets—educational materials and information systems literature—the authors propose a three-stage zero-shot prompting strategy tailored for GPT-5 and conduct an end-to-end comparison against an FCA-based approach implemented via the CREA pipeline, covering the full workflow of topic extraction, merging, and labeling. Experimental results indicate that LLMs excel in semantic richness and flexibility, whereas FCA demonstrates superior structured representation and interpretability. This work presents the first systematic benchmarking of these two paradigms in real-world scenarios, offering empirical evidence and technical guidance for future method selection in topic modeling.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Topic discovery and tracking

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.

Problem

• Topic Modeling
• Large Language Model
• Formal Concept Analysis
• Comparative Study

Innovation

• Large Language Model
• Formal Concept Analysis
• Topic Modeling
• Zero-shot Prompting
• CREA Pipeline