Skip to main navigation Skip to search Skip to main content

Prompting large language models for topic modeling

  • Han Wang*
  • , Nirmalendu Prakash
  • , Nguyen Khoi Hoang
  • , Ming Shan Hee
  • , Usman Naseem
  • , Roy Ka Wei Lee
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words. Moreover, these models often neglect sentence-level semantics, focusing primarily on token-level semantics. In this paper, we propose PromptTopic, a novel topic modeling approach that harnesses the advanced language understanding of large language models (LLMs) to address these challenges. It involves extracting topics at the sentence level from individual documents, then aggregating and condensing these topics into a predefined quantity, ultimately providing coherent topics for texts of varying lengths. This approach eliminates the need for manual parameter tuning and improves the quality of extracted topics. We benchmark PromptTopic against the state-of-the-art baselines on three vastly diverse datasets, establishing its proficiency in discovering meaningful topics. Furthermore, qualitative analysis showcases PromptTopic's ability to uncover relevant topics in multiple datasets.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Big Data
Subtitle of host publicationproceedings
EditorsJingrui He, Themis Palpanas, Xiaohua Hu, Alfredo Cuzzocrea, Dejing Dou, Dominik Slezak, Wei Wang, Aleksandra Gruca, Jerry Chun-Wei Lin, Rakesh Agrawal
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1236-1241
Number of pages6
ISBN (Electronic)9798350324457
ISBN (Print)9798350324464
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event2023 IEEE International Conference on Big Data, BigData 2023 - Sorrento, Italy
Duration: 15 Dec 2023 → 18 Dec 2023

Conference

Conference2023 IEEE International Conference on Big Data, BigData 2023
Country/TerritoryItaly
CitySorrento
Period15/12/23 → 18/12/23

Fingerprint

Dive into the research topics of 'Prompting large language models for topic modeling'. Together they form a unique fingerprint.

Cite this