NTLRAG: Narrative Topic Labels derived with Retrieval Augmented Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915807028576256 |
|---|---|
| author | Grobelscheg, Lisa Kahr, Ema Strembeck, Mark |
| author_facet | Grobelscheg, Lisa Kahr, Ema Strembeck, Mark |
| contents | Topic modeling has evolved as an important means to identify evident or hidden topics within large collections of text documents. Topic modeling approaches are often used for analyzing and making sense of social media discussions consisting of millions of short text messages. However, assigning meaningful topic labels to document clusters remains challenging, as users are commonly presented with unstructured keyword lists that may not accurately capture the respective core topic. In this paper, we introduce Narrative Topic Labels derived with Retrieval Augmented Generation (NTLRAG), a scalable and extensible framework that generates semantically precise and human-interpretable narrative topic labels. Our narrative topic labels provide a context-rich, intuitive concept to describe topic model output. In particular, NTLRAG uses retrieval augmented generation (RAG) techniques and considers multiple retrieval strategies as well as chain-of-thought elements to provide high-quality output. NTLRAG can be combined with any standard topic model to generate, validate, and refine narratives which then serve as narrative topic labels. We evaluated NTLRAG with a user study and three real-world datasets consisting of more than 6.7 million social media messages that have been sent by more than 2.7 million users. The user study involved 16 human evaluators who found that our narrative topic labels offer superior interpretability and usability as compared to traditional keyword lists. An implementation of NTLRAG is publicly available for download. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17216 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NTLRAG: Narrative Topic Labels derived with Retrieval Augmented Generation Grobelscheg, Lisa Kahr, Ema Strembeck, Mark Social and Information Networks I.2.7; J.4 Topic modeling has evolved as an important means to identify evident or hidden topics within large collections of text documents. Topic modeling approaches are often used for analyzing and making sense of social media discussions consisting of millions of short text messages. However, assigning meaningful topic labels to document clusters remains challenging, as users are commonly presented with unstructured keyword lists that may not accurately capture the respective core topic. In this paper, we introduce Narrative Topic Labels derived with Retrieval Augmented Generation (NTLRAG), a scalable and extensible framework that generates semantically precise and human-interpretable narrative topic labels. Our narrative topic labels provide a context-rich, intuitive concept to describe topic model output. In particular, NTLRAG uses retrieval augmented generation (RAG) techniques and considers multiple retrieval strategies as well as chain-of-thought elements to provide high-quality output. NTLRAG can be combined with any standard topic model to generate, validate, and refine narratives which then serve as narrative topic labels. We evaluated NTLRAG with a user study and three real-world datasets consisting of more than 6.7 million social media messages that have been sent by more than 2.7 million users. The user study involved 16 human evaluators who found that our narrative topic labels offer superior interpretability and usability as compared to traditional keyword lists. An implementation of NTLRAG is publicly available for download. |
| title | NTLRAG: Narrative Topic Labels derived with Retrieval Augmented Generation |
| topic | Social and Information Networks I.2.7; J.4 |
| url | https://arxiv.org/abs/2602.17216 |