Review of Passenger Flow Modelling Approaches Based on a Bibliometric Analysis

TL;DR

This paper analyzes the evolution of passenger flow forecasting research, highlighting methodological shifts, identifying gaps, and emphasizing the growing importance of deep learning and foundation models in the field.

Contribution

It provides a comprehensive bibliometric analysis of passenger flow modeling, revealing research trends, methodological shifts, and identifying key gaps and future directions.

Findings

Research activity increased after 2008 with a shift to deep learning.

Identified gaps include data fusion limitations and interpretability challenges.

Growth in foundation models' relevance was observed.

Abstract

This paper presents a bibliometric analysis of the field of short-term passenger flow forecasting within local public transit, covering 814 publications that span from 1984 to 2024. In addition to common bibliometric analysis tools, a variant of a citation network was developed, and topic modelling was conducted. The analysis reveals that research activity exhibited sporadic patterns prior to 2008, followed by a marked acceleration, characterised by a shift from conventional statistical and machine learning methodologies (e.g., ARIMA, SVM, and basic neural networks) to specialised deep learning architectures. Based on this insight, a connection to more general fields such as machine learning and time series modelling was established. In addition to modelling, spatial, linguistic, and modal biases were identified and findings from existing secondary literature were validated and quantified. This revealed existing gaps, such as constrained data fusion, open (multivariate) data, and underappreciated challenges related to model interpretability, cost-efficiency, and a balance between algorithmic performance and practical deployment considerations. In connection with the superordinate fields, the growth in relevance of foundation models is also noteworthy.