Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets

Wangjiaxuan Xin, Shuhua Yin, Shi Chen, Yaorong Ge

TL;DR

TM-Rephrase introduces a model-agnostic, LLM-driven rephrasing framework that standardizes noisy, short social media text prior to topic discovery. By comparing general and colloquial-to-formal rephrasing, the study shows substantial gains in topic coherence, uniqueness, and diversity across LDA, BERTopic, FASTopic, and TSCTM on 25,027 COVID-19-related tweets, with the colloquial-to-formal scheme yielding the strongest results for several models. The approach enhances interpretability of public-health discourse and crisis informatics analyses, while maintaining a data-centric, input-quality improvement stance rather than altering the underlying topic models. Limitations include evaluation on a single domain and LLM, suggesting future work on cross-domain generalization, adaptive prompts, and deeper qualitative assessments.

Abstract

Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder the effectiveness of traditional topic modeling, producing incoherent or redundant topics that are often difficult to interpret. To address these challenges, we have developed \emph{TM-Rephrase}, a model-agnostic framework that leverages large language models (LLMs) to rephrase raw tweets into more standardized and formal language prior to topic modeling. Using a dataset of 25,027 COVID-19-related Twitter posts, we investigate the effects of two rephrasing strategies, general- and colloquial-to-formal-rephrasing, on multiple topic modeling methods. Results demonstrate that \emph{TM-Rephrase} improves three metrics measuring topic modeling performance (i.e., topic coherence, topic uniqueness, and topic diversity) while reducing topic redundancy of most topic modeling algorithms, with the colloquial-to-formal strategy yielding the greatest performance gains and especially for the Latent Dirichlet Allocation (LDA) algorithm. This study contributes to a model-agnostic approach to enhancing topic modeling in public health related social media analysis, with broad implications for improved understanding of public discourse in health crisis as well as other important domains.

Improving Topic Modeling of Social Media Short Texts with Rephrasing: A Case Study of COVID-19 Related Tweets

TL;DR

TM-Rephrase introduces a model-agnostic, LLM-driven rephrasing framework that standardizes noisy, short social media text prior to topic discovery. By comparing general and colloquial-to-formal rephrasing, the study shows substantial gains in topic coherence, uniqueness, and diversity across LDA, BERTopic, FASTopic, and TSCTM on 25,027 COVID-19-related tweets, with the colloquial-to-formal scheme yielding the strongest results for several models. The approach enhances interpretability of public-health discourse and crisis informatics analyses, while maintaining a data-centric, input-quality improvement stance rather than altering the underlying topic models. Limitations include evaluation on a single domain and LLM, suggesting future work on cross-domain generalization, adaptive prompts, and deeper qualitative assessments.

Abstract

Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder the effectiveness of traditional topic modeling, producing incoherent or redundant topics that are often difficult to interpret. To address these challenges, we have developed \emph{TM-Rephrase}, a model-agnostic framework that leverages large language models (LLMs) to rephrase raw tweets into more standardized and formal language prior to topic modeling. Using a dataset of 25,027 COVID-19-related Twitter posts, we investigate the effects of two rephrasing strategies, general- and colloquial-to-formal-rephrasing, on multiple topic modeling methods. Results demonstrate that \emph{TM-Rephrase} improves three metrics measuring topic modeling performance (i.e., topic coherence, topic uniqueness, and topic diversity) while reducing topic redundancy of most topic modeling algorithms, with the colloquial-to-formal strategy yielding the greatest performance gains and especially for the Latent Dirichlet Allocation (LDA) algorithm. This study contributes to a model-agnostic approach to enhancing topic modeling in public health related social media analysis, with broad implications for improved understanding of public discourse in health crisis as well as other important domains.
Paper Structure (18 sections, 2 figures, 7 tables)

This paper contains 18 sections, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Topic Modeling for Social Media Short Text
  4. Public Discourse during the COVID-19 Pandemic
  5. Proposed Framework
  6. Data Collection
  7. LLM-based Rephrasing
  8. Data Preprocessing
  9. Topic Evaluation
  10. Experiments
  11. Dataset
  12. Topic Models and LLM Selection
  13. Hyperparameters
  14. Performance Metrics
  15. Results and Discussion
  16. ...and 3 more sections

Figures (2)

  • Figure 1: Overview of the TM-Rephrase framework. The pipeline integrates data collection and preprocessing, LLM-based rephrasing, and topic modeling with evaluation.
  • Figure 2: Outline of the topic evaluation process. Both the original and rephrased tweets were modeled using the same topic models, and the resulting topics were compared and evaluated through quantitative metrics and qualitative expert judgment.