Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909541311971328 |
|---|---|
| author | Spielberger, Gerion Artinger, Florian M. Reb, Jochen Kerschreiter, Rudolf |
| author_facet | Spielberger, Gerion Artinger, Florian M. Reb, Jochen Kerschreiter, Rudolf |
| contents | Analyzing textual data is the cornerstone of qualitative research. While traditional methods such as grounded theory and content analysis are widely used, they are labor-intensive and time-consuming. Topic modeling offers an automated complement. Yet, existing approaches, including LLM-based topic modeling, still struggle with issues such as high data preprocessing requirements, interpretability, and reliability. This paper introduces Agentic Retrieval-Augmented Generation (Agentic RAG) as a method for topic modeling with LLMs. It integrates three key components: (1) retrieval, enabling automatized access to external data beyond an LLM's pre-trained knowledge; (2) generation, leveraging LLM capabilities for text synthesis; and (3) agent-driven learning, iteratively refining retrieval and query formulation processes. To empirically validate Agentic RAG for topic modeling, we reanalyze a Twitter/X dataset, previously examined by Mu et al. (2024a). Our findings demonstrate that the approach is more efficient, interpretable and at the same time achieves higher reliability and validity in comparison to the standard machine learning approach but also in comparison to LLM prompting for topic modeling. These results highlight Agentic RAG's ability to generate semantically relevant and reproducible topics, positioning it as a robust, scalable, and transparent alternative for AI-driven qualitative research in leadership, managerial, and organizational research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20963 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration Spielberger, Gerion Artinger, Florian M. Reb, Jochen Kerschreiter, Rudolf Machine Learning Artificial Intelligence General Economics Economics Analyzing textual data is the cornerstone of qualitative research. While traditional methods such as grounded theory and content analysis are widely used, they are labor-intensive and time-consuming. Topic modeling offers an automated complement. Yet, existing approaches, including LLM-based topic modeling, still struggle with issues such as high data preprocessing requirements, interpretability, and reliability. This paper introduces Agentic Retrieval-Augmented Generation (Agentic RAG) as a method for topic modeling with LLMs. It integrates three key components: (1) retrieval, enabling automatized access to external data beyond an LLM's pre-trained knowledge; (2) generation, leveraging LLM capabilities for text synthesis; and (3) agent-driven learning, iteratively refining retrieval and query formulation processes. To empirically validate Agentic RAG for topic modeling, we reanalyze a Twitter/X dataset, previously examined by Mu et al. (2024a). Our findings demonstrate that the approach is more efficient, interpretable and at the same time achieves higher reliability and validity in comparison to the standard machine learning approach but also in comparison to LLM prompting for topic modeling. These results highlight Agentic RAG's ability to generate semantically relevant and reproducible topics, positioning it as a robust, scalable, and transparent alternative for AI-driven qualitative research in leadership, managerial, and organizational research. |
| title | Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration |
| topic | Machine Learning Artificial Intelligence General Economics Economics |
| url | https://arxiv.org/abs/2502.20963 |