Back to all available

Hybrid topic modelling and network analysis for urban traffic research using TF‑IDF and NMF

artificial-intelligence
data-mining-and-machine-learning
data-science
network-science-and-online-social-networks
text-mining

Abstract

Urban traffic systems generate vast amounts of research data, reflecting evolving challenges and innovations in mobility. To uncover latent themes and their interconnections in the urban traffic literature, this study proposes a hybrid text-mining approach that combines topic modelling and network analysis. We analyze 88 traffic-related research papers published from 2016 to 2025, focusing on titles, abstracts, and author keywords. A Term Frequency–Inverse Document Frequency (TF‑IDF) vectorization with Non-Negative Matrix Factorization (NMF) identifies five salient topics, which are interpreted to represent key research themes (e.g., traffic flow prediction, smart mobility analytics, trajectory and travel behaviour analysis, congestion and network management, and graph-based machine learning for transport). Each document is assigned a dominant topic, and the distribution of documents across these topics is visualized. We further construct a keyword co-occurrence network to elucidate how author-provided keywords cluster into thematic groups and interlink across publications. Temporal analysis reveals how topic prevalence has shifted annually from 2016 to 2025, highlighting emerging and declining research trends. Our findings indicate a growing prominence of data-driven and AI-powered methods in recent years, alongside enduring interest in traffic flow and congestion issues. The proposed hybrid approach yields a comprehensive landscape of urban traffic research, integrating quantitative topic modelling with network-based insights. We highlight three primary contributions: (1) a methodological framework that fuses TF‑IDF, NMF topic modelling, and co-occurrence network analysis for urban research text mining, (2) an application of topic modelling to illuminate evolving themes in urban traffic literature, and (3) visualization-driven, network-based insights that reveal thematic clusters and keyword interlinkages in the field. These contributions demonstrate how combining text analytics with network science can support urban computing research by mapping knowledge domains and guiding future studies.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].