GLMTopic: A Hybrid Chinese Topic Model Leveraging Large Language Models

Chen, W; Hussain, W; Chen, J

GLMTopic: A Hybrid Chinese Topic Model Leveraging Large Language Models

Chen, W Hussain, W

Chen, J

Permalink

Publisher:: TECH SCIENCE PRESS
Publication Type:: Journal Article
Citation:: Computers Materials and Continua, 2025, 85, (1), pp. 1559-1583
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (27.51 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Chen, W
dc.contributor.author	Hussain, W https://orcid.org/0000-0003-0610-4006
dc.contributor.author	Chen, J
dc.date.accessioned	2026-01-28T01:03:39Z
dc.date.available	2026-01-28T01:03:39Z
dc.date.issued	2025-01-01
dc.identifier.citation	Computers Materials and Continua, 2025, 85, (1), pp. 1559-1583
dc.identifier.issn	1546-2218
dc.identifier.issn	1546-2226
dc.identifier.uri	http://hdl.handle.net/10453/192455
dc.description.abstract	Topic modeling is a fundamental technique of content analysis in natural language processing, widely applied in domains such as social sciences and finance. In the era of digital communication, social scientists increasingly rely on large-scale social media data to explore public discourse, collective behavior, and emerging social concerns. However, traditional models like Latent Dirichlet Allocation (LDA) and neural topic models like BERTopic struggle to capture deep semantic structures in short-text datasets, especially in complex non-English languages like Chinese. This paper presents Generative Language Model Topic (GLMTopic) a novel hybrid topic modeling framework leveraging the capabilities of large language models, designed to support social science research by uncovering coherent and interpretable themes from Chinese social media platforms. GLMTopic integrates Adaptive Community-enhanced Graph Embedding for advanced semantic representation, Uniform Manifold Approximation and Projection-based (UMAP-based) dimensionality reduction, Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) clustering, and large language model-powered (LLM-powered) representation tuning to generate more contextually relevant and interpretable topics. By reducing dependence on extensive text preprocessing and human expert intervention in post-analysis topic label annotation, GLMTopic facilitates a fully automated and user-friendly topic extraction process. Experimental evaluations on a social media dataset sourced from Weibo demonstrate that GLMTopic outperforms Latent Dirichlet Allocation (LDA) and BERTopic in coherence score and usability with automated interpretation, providing a more scalable and semantically accurate solution for Chinese topic modeling. Future research will explore optimizing computational efficiency, integrating knowledge graphs and sentiment analysis for more complicated workflows, and extending the framework for real-time and multilingual topic modeling.
dc.language	English
dc.publisher	TECH SCIENCE PRESS
dc.relation.ispartof	Computers Materials and Continua
dc.relation.isbasedon	10.32604/cmc.2025.065916
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0103 Numerical and Computational Mathematics, 0912 Materials Engineering, 0915 Interdisciplinary Engineering
dc.subject.classification	Applied Mathematics
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	GLMTopic: A Hybrid Chinese Topic Model Leveraging Large Language Models
dc.type	Journal Article
utslib.citation.volume	85
utslib.for	0103 Numerical and Computational Mathematics
utslib.for	0912 Materials Engineering
utslib.for	0915 Interdisciplinary Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-01-28T01:03:37Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	85
utslib.citation.issue	1

Abstract:

Topic modeling is a fundamental technique of content analysis in natural language processing, widely applied in domains such as social sciences and finance. In the era of digital communication, social scientists increasingly rely on large-scale social media data to explore public discourse, collective behavior, and emerging social concerns. However, traditional models like Latent Dirichlet Allocation (LDA) and neural topic models like BERTopic struggle to capture deep semantic structures in short-text datasets, especially in complex non-English languages like Chinese. This paper presents Generative Language Model Topic (GLMTopic) a novel hybrid topic modeling framework leveraging the capabilities of large language models, designed to support social science research by uncovering coherent and interpretable themes from Chinese social media platforms. GLMTopic integrates Adaptive Community-enhanced Graph Embedding for advanced semantic representation, Uniform Manifold Approximation and Projection-based (UMAP-based) dimensionality reduction, Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) clustering, and large language model-powered (LLM-powered) representation tuning to generate more contextually relevant and interpretable topics. By reducing dependence on extensive text preprocessing and human expert intervention in post-analysis topic label annotation, GLMTopic facilitates a fully automated and user-friendly topic extraction process. Experimental evaluations on a social media dataset sourced from Weibo demonstrate that GLMTopic outperforms Latent Dirichlet Allocation (LDA) and BERTopic in coherence score and usability with automated interpretation, providing a more scalable and semantically accurate solution for Chinese topic modeling. Future research will explore optimizing computational efficiency, integrating knowledge graphs and sentiment analysis for more complicated workflows, and extending the framework for real-time and multilingual topic modeling.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/192455