Exploring Topic Trends in COVID-19 Research Literature using Non-Negative Matrix Factorization

2025-03-23

AI Summary

This study investigates the thematic evolution of COVID-19 scientific literature. To address the challenge of dynamically identifying robust, interpretable topics over time, we propose an integrated analytical framework leveraging TF-IDF weighting, context-aware text preprocessing, and non-negative matrix factorization (NMF) topic modeling. Crucially, we introduce— for the first time in this domain—a systematic NMF stability analysis to objectively determine the optimal number of topics, overcoming the subjectivity and limitations of empirical heuristics. By tracking temporal distributions and semantic shifts of topics, we identify stable, semantically coherent thematic clusters and quantify their stage-wise evolutionary patterns. The method unifies static topic structure discovery with dynamic longitudinal analysis, enabling rigorous, reproducible evaluation of topic models. It provides a novel methodological foundation for pandemic-related research landscape monitoring, knowledge graph construction, and evidence-based science policy support.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Application Domains: Humanities & Computational Social Science

Application Category

• Web Mining and Content Analysis: Topic discovery and tracking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In this work, we apply topic modeling using Non-Negative Matrix Factorization (NMF) on the COVID-19 Open Research Dataset (CORD-19) to uncover the underlying thematic structure and its evolution within the extensive body of COVID-19 research literature. NMF factorizes the document-term matrix into two non-negative matrices, effectively representing the topics and their distribution across the documents. This helps us see how strongly documents relate to topics and how topics relate to words. We describe the complete methodology which involves a series of rigorous pre-processing steps to standardize the available text data while preserving the context of phrases, and subsequently feature extraction using the term frequency-inverse document frequency (tf-idf), which assigns weights to words based on their frequency and rarity in the dataset. To ensure the robustness of our topic model, we conduct a stability analysis. This process assesses the stability scores of the NMF topic model for different numbers of topics, enabling us to select the optimal number of topics for our analysis. Through our analysis, we track the evolution of topics over time within the CORD-19 dataset. Our findings contribute to the understanding of the knowledge structure of the COVID-19 research landscape, providing a valuable resource for future research in this field.

Problem

• Uncover thematic structure in COVID-19 research literature
• Track evolution of topics over time in CORD-19 dataset
• Ensure robustness of topic model via stability analysis

Innovation

• Uses Non-Negative Matrix Factorization for topic modeling
• Applies tf-idf for feature extraction in text data
• Conducts stability analysis to optimize topic count