Discovering Latent Topics and Trends in Traffic‐Related Research Within AI Literature Using Structural Topic Modelling
IET Intelligent Transport Systems · 2026-01 · 20 (1)
DOI: 10.1049/itr2.70235 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Intelligent Transport Systems, online erschienen am 15.05.2026. Verfasst von Qinghong Liu und 1 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Although there are numerous bibliometric studies on research trends in the transportation field, they generally focus on mainstream journals in transportation, while the publications in the computer field are usually ignored. To fill this gap, this paper adopts a new perspective: it collects relevant data from China Computer Federation (CCF)‐A and CCF‐B class AI journals and conferences and conducts a comprehensive analysis for the papers about traffic engineering. We find the differences between a journal and a conference are obvious. For example, the proportion of traffic‐related papers in journals has shown greater growth; the distribution of keywords in journals is more scattered; institutions from the USA have made greater contributions to conference papers, while those from China have published more journal papers. When using structural topic model for topic modelling and Vosviewer for network relationship analysis, we find that conference papers contain more topics related to autonomous driving and trajectory prediction, while journal papers include more research on the rigour and stability of the algorithms. In addition, a new analysis about the recent update of large language model‐related papers within the literature data is given. In other words, the results in this paper could help understand the current trends of AI‐related research in the transportation field.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, Q., & Jin, C. (2026). Discovering Latent Topics and Trends in Traffic‐Related Research Within AI Literature Using Structural Topic Modelling. IET Intelligent Transport Systems, 20(1). https://doi.org/10.1049/itr2.70235
Vancouver
Liu Q, Jin C. Discovering Latent Topics and Trends in Traffic‐Related Research Within AI Literature Using Structural Topic Modelling. IET Intelligent Transport Systems. 2026;20(1). doi:10.1049/itr2.70235
BibTeX
@article{Liu2026,
author = {Liu, Qinghong and Jin, Cheng‐Jie},
title = {Discovering Latent Topics and Trends in Traffic‐Related Research Within AI Literature Using Structural Topic Modelling},
journal = {IET Intelligent Transport Systems},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/itr2.70235}
}
EUVIMED