Journal of Public Transportation最新文献

{"title":"LingoTrip: Spatiotemporal context prompt driven large language model for individual trip prediction","authors":"Zhenlin Qin ,&nbsp;Pengfei Zhang ,&nbsp;Leizhen Wang ,&nbsp;Zhenliang Ma","doi":"10.1016/j.jpubtr.2025.100117","DOIUrl":"10.1016/j.jpubtr.2025.100117","url":null,"abstract":"<div><div>Large language models (LLMs) showed superior performance in many language-related tasks. It is promising to model the individual mobility prediction problem as a language model and use pretrained LLMs to predict the individual next trip information (e.g., time and location) for personalized travel recommendations. Theoretically, it is expected to overcome the common limitations of data-driven prediction models in zero/few shot learning, generalization, and interpretability. The paper proposes a LingoTrip model for predicting individual next trip location by designing the spatiotemporal context prompts for LLMs. The designed prompting strategies enable LLMs to capture implicit land use information (trip purposes), spatiotemporal mobility patterns (choice preferences), and geographical dependencies of the stations used (choice variability). The lingoTrip is validated using Hong Kong Mass Transit Railway trip data by comparing it with the state-of-the-art data-driven mobility prediction models under different training data sizes. Sensitivity analyses are performed for model hyperparameters and their tuning methods to adapt for other datasets. The results show that LingoTrip outperforms data-driven models in terms of prediction accuracy, transferability (between individuals), zero/few shot learning (limited training sample size) and interpretability of predictions. The LingoTrip model can facilitate the effective provision of personalized information for system crowding and disruption contexts (i.e., proactively providing information to targeted individuals).</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100117"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143167473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Travel adaptations among women commuters in response to sexual harassment and fear of crime on public transport","authors":"Elisa Alfaro ,&nbsp;Oscar Oviedo-Trespalacios ,&nbsp;Francisco Alonso ,&nbsp;Sergio A. Useche","doi":"10.1016/j.jpubtr.2025.100130","DOIUrl":"10.1016/j.jpubtr.2025.100130","url":null,"abstract":"<div><div>Promoting public transport is widely regarded as a key strategy for advancing sustainability. However, concerns about women’s safety continue to pose a significant barrier to its regular use. A growing number of studies have highlighted the vulnerability of female commuters to harassment and crime, yet there is limited evidence on how these experiences –and the fears they generate– translate into changes in travel behavior. This knowledge gap makes it difficult to develop evidence-based interventions. Accordingly, this study examined the interrelations between sexual harassment, fear of crime, and travel-related behavioral adaptations among female public transport users in Spain. The analysis was based on a cross-sectional sample of 720 female public transport commuters. The average age of participants was 29 years. They responded to an e-survey addressing commuting patterns, perceptions of safety, and behavioral responses. Our results suggest that both direct and indirect experiences of harassment are consistently associated with higher levels of fear of crime, which in turn influence changes in travel behavior. Specifically, fear of crime was found to partially mediate the relationship between harassment and travel-related adaptations. These findings provide further insight into how psychological and contextual factors shape women’s use of public transport, and highlight the need to address not only actual incidents but also the broader perception of insecurity.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100130"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The personal safety burden for women taking public transport in Australia and implications for provision of equitable public transport","authors":"Julie A. King ,&nbsp;Dominique A. Greer ,&nbsp;Rae S.M. Danvers ,&nbsp;Byron W. Keating","doi":"10.1016/j.jpubtr.2025.100118","DOIUrl":"10.1016/j.jpubtr.2025.100118","url":null,"abstract":"<div><div>Travel on public transport for women is associated with concerns about safety from harassment and violence, and women may avoid public transport or make changes to their travel as a consequence. This qualitative research aimed to explore women’s experiences on public transport, the steps they take to avoid harassment and violence, and what they thought could be done to improve their safety. Women (n = 44) in Australia’s two largest cities, Sydney and Melbourne, were recruited for focus group discussions and their responses were analysed thematically. The results showed that women experience a personal safety burden, due to the need to anticipate possible exposure to harassment and violence, plan ways of avoiding or mitigating the risk, and use defensive tactics to cope with uncomfortable situations. This personal safety burden has five dimensions: cognitive, temporal, emotional, financial and social. The responses showed that women tended to take the public transport system as a given, and to believe they needed to take responsibility for their own safety, so that they did not nominate particular solutions for public transport providers to implement. However, it was evident that the features of public transport travel that participants felt were safer, such as the presence of trained staff, are diminishing with the move to greater use of technology and automation. It is considered that public transport providers have an obligation to ensure that women are not disadvantaged by the personal safety burden observed in this research. It is recommended that public transport providers note the existing features that women find safer (e.g., well-lit environment, presence of trained staff) and seek to extend their provision; and investigate innovative means of maintaining and enhancing safety for women while pursing technological change.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100118"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143168293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The influence of walking accessibility on station-to-station passenger flow and its interaction with metropolitan race/class segregation: A case study of MARTA’s heavy-rail network, Atlanta (USA)","authors":"Luis Enrique Ramos-Santiago ,&nbsp;Luke Derochers","doi":"10.1016/j.jpubtr.2024.100115","DOIUrl":"10.1016/j.jpubtr.2024.100115","url":null,"abstract":"<div><div>Mass transit is a key transport strategy in helping cities decarbonize, adapt to an era of rapid climate change, and guide rapid urbanization. Central to transit planning is the ability to accurately estimate demand for an effective, efficient, and equitable infrastructure and services. Instrumental to this effort is direct-demand modelling (DDM), which has evolved to become more nuanced in predicting ridership at station-level and station-<em>to</em>-station levels and in shedding light on key ridership and performance determinants. <em>Local</em> and <em>Metropolitan</em> accessibility as predictors of transit patronage has been shown significant in recent DDM studies at station-level, with an apparent synergistic relationship. This, however, has not been explored on a station-<em>to</em>-station passenger flow level. In several ways this is a more valid unit of analysis for rail ridership studies as it captures critical factors between and at both ends of the trip that are experienced by the passenger. It is also well documented that the sensitivity of passengers to key ridership determinants varies across income levels. In some jurisdictions income level strongly correlates with race/ethnicity and/or class, due in part to historical legacies of classism and/or racism. Segregation because of class and/or race prejudice, often found in US cities, might yield spatial heterogeneity in whole-network DDM model parameters and introduce bias that could potentially mislead transit analysts, policy makers, and systemwide effectiveness. We explored and tested these possibilities and considered modelling and policy implications as we leveraged Atlanta’s legacy of racial and income segregation in studying MARTA’s Origin-Destination (O-D) passenger flow patterns. First, a potential synergistic relationship between origin-stations’ and destination-stations’ walking accessibility levels was tested. Disparities, if any, in this and other ridership determinants were then explored between two distinct sets of O-D pairs whose origin Pedsheds accommodate majority-white or majority-nonwhite residents. Comparison and testing using generalized crossed-effects modelling reveals important differences in fit, magnitude, and significance of some parameters across submodels and as compared to the whole-network model. We also identified distinct moderating effects of distance between O-D pair stations and walking accessibility levels across submodels. In racially- and/or class-segregated cities planners would benefit from developing race- and/or class-based DDM submodels that would likely yield less biassed parameters; improve our understanding of rail transit patronage determinants; and help in crafting more effective and equitable transit and land-use policies.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100115"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143168294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A planning history of high-speed rail in Italy","authors":"Marco Chitti ,&nbsp;Paolo Beria","doi":"10.1016/j.jpubtr.2025.100126","DOIUrl":"10.1016/j.jpubtr.2025.100126","url":null,"abstract":"<div><div>The paper examines the planning history of the Italian high-speed rail (HSR) network through three main perspectives: the distinction between service-driven and infrastructure-driven planning paradigms, the characteristics of infrastructure megaprojects, and the debates surrounding core and periphery regions. It divides this planning history into four key phases spanning nearly four decades, each marked by shifts in governance and planning philosophy. The paper evaluates the strengths and weaknesses of each phase, focusing not only on outcomes but also on the coherence of planning efforts. The Italian case serves as a basis for a broader discussion on the challenges of infrastructure-centered planning in rail transport.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100126"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144335719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Re-evaluating the satisfaction effects of rail transit accessibility: A comparison of local and network perspectives","authors":"Yanwen Yun ,&nbsp;Jingtong Zhai","doi":"10.1016/j.jpubtr.2025.100131","DOIUrl":"10.1016/j.jpubtr.2025.100131","url":null,"abstract":"<div><div>Previous studies have linked public transport accessibility to travel satisfaction, but most focus on local accessibility effects, with limited research comparing these to network accessibility effects. Using data from the Beijing Rail Transit System (BRTS) and a large-scale household satisfaction survey, this study applies a Bayesian multilevel approach to examine and compare the impacts of local and network rail transit accessibility on travel satisfaction. We also explore the nonlinear nature of this relationship and the influence of rail transit configurations. The results show that: 1) Both local and network accessibility have significant effects on travel satisfaction, including for commuting and non-commuting trips. Local accessibility has a stronger impact than network accessibility. 2) The effect is nonlinear, peaking at the fourth quintile, and from the second quintile onward, local accessibility has a clearly stronger positive effect than network accessibility. 3) Residents near ring lines or non-transfer stations tend to benefit more from accessibility improvements. These findings suggest that urban planners and policymakers should evaluate transit investments based on network accessibility beyond just station areas, while accounting for threshold effects and rail network design to promote transport equity and overall welfare.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100131"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How flexible transportation services work in reality?- some insights from real-world observations","authors":"Ran Du ,&nbsp;Fumitaka Kurauchi ,&nbsp;Toshiyuki Nakamura ,&nbsp;Masahiro Kuwahara","doi":"10.1016/j.jpubtr.2025.100121","DOIUrl":"10.1016/j.jpubtr.2025.100121","url":null,"abstract":"<div><div>Public transportation in Japan currently faces serious challenges, including depopulation, dispersed low demand, and a shortage of drivers. To address these issues and cover wider areas with fewer drivers, flexible transport systems like demand-responsive transport (DRT) services are becoming increasingly popular, particularly in rural areas, thanks to recent advancements in Information and Communication Technologies (ICT). Despite the potential for reduced operational costs through more efficient service provision, overall costs often remain high due to increased operator and system costs. Improving the efficiency of services is crucial even for flexible transport systems. Understanding detailed traveler behaviors within these systems is essential for this purpose.</div><div>Flexible transport systems often incorporate online booking and vehicle assignment systems, allowing for the automatic collection of booking data. By analyzing this data, we can gain insights into the behaviors of travelers and the patterns of bus stop utilization. This study utilizes booking data to examine the interactions between passengers and bus stops in flexible transport systems, with a particular focus on understanding and discussing patterns of regularity and variability in both traveler behavior and bus stop usage.</div><div>The study uses nine years of booking data (2015–2023) from a mid-sized city in Gifu Prefecture, encompassing 845 passengers and 142,638 records. The analysis first explores the regularity of traveler behaviors and bus stop usage patterns, followed by a discussion on the flexibility or variability of vehicle movements.</div><div>The results show that vehicle movements are primarily driven by regular high-frequency travelers, who use the service for commuting and returning home. This dominance often excludes low-frequency random travelers from accessing the service. Additionally, it is suggested that minimizing total operational costs may not adequately assign travelers onto vehicles, and the implementation of monthly passes may further reinforce the dominance of high-frequency travelers.</div><div>These insights underscore the importance of considering service designs from various dimensions, including user behavior, spatial factors, and temporal patterns, for the effective optimization of flexible transport systems.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100121"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring antecedents of passengers’ behavioral intentions toward autonomous buses: A decomposed planning behavior approach","authors":"Kai-Chieh Hu ,&nbsp;Li-Hao Yang","doi":"10.1016/j.jpubtr.2025.100116","DOIUrl":"10.1016/j.jpubtr.2025.100116","url":null,"abstract":"<div><div>The increasing prominence of autonomous buses in metropolitan transportation has sparked considerable interest. However, the absence of a comprehensive theoretical framework hinders the systematic exploration of factors influencing passengers’ behavioral intentions regarding autonomous buses. This study addresses this gap by employing the decomposed planning behavior theory to investigate the antecedents of passengers’ behavioral intentions. Additionally, the study examines the impact of travel anxiety and perceived risk on passengers’ attitudes. Data were collected through a questionnaire survey, and structural equation modeling was utilized to rigorously test the research model. The findings reveal that purchase intention is positively influenced by novelty seeking, subjective norm, and perceived behavioral control, while being negatively impacted by travel anxiety. Conversely, travel anxiety is negatively influenced by novelty seeking but positively affected by perceived risk. Moreover, interpersonal influence positively affects subjective norm, and self-efficacy has a positive influence on perceived behavioral control. This study offers valuable insights for current and potential bus operators and government entities seeking to advance the promotion of autonomous buses in metropolitan areas.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100116"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143319507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven causal behaviour modelling from trajectory data: A case for fare incentives in public transport","authors":"Yuanyuan Wu ,&nbsp;Alex Markham ,&nbsp;Leizhen Wang ,&nbsp;Liam Solus ,&nbsp;Zhenliang Ma","doi":"10.1016/j.jpubtr.2024.100114","DOIUrl":"10.1016/j.jpubtr.2024.100114","url":null,"abstract":"<div><div>Behaviour modelling has been widely explored using both statistical and machine learning techniques, primarily relying on analyzing correlations to understand passenger responses under different conditions and scenarios. However, correlation alone does not imply causation. This paper introduces a data-driven causal behaviour modelling approach, comprising two phases: causal discovery and causal inference. Causal discovery phase uses Peter-Clark (PC) algorithm to learn a directed acyclic graph that captures the causal relationships among variables. Causal inference phase estimates the corresponding model parameters and infers (conditional) causal effects of interventions designed to influence user behaviour. The method is validated by comparing the results with those from conventional modelling approaches (logistic regression and expert knowledge) using smart card data from a real-world use case on a pre-peak fare discount incentive program in the Hong Kong Mass Transit Railway system. The results highlight that the purely data-driven causal discovery method can produce reasonable causal graph. The method can also quantify the behavioural impacts of the incentive, identify key influencing factors, and estimate the corresponding causal effects. The overall causal effect of the incentive is approximately 0.7 %, with about 3 % of the population changing behaviour from previous statistical analysis. Interestingly, passengers with the highest flexibility exhibit a negative response, while those with medium-to-high flexibility demonstrate 3 times of the general level of responsiveness. The approach initiates the data-driven, causal modelling of human behaviour dynamics to support policy developments and managerial interventions.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100114"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143168444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting and analyzing ferry transit delays using open data and machine learning","authors":"Malek Sarhani ,&nbsp;Abtin Nourmohammadzadeh ,&nbsp;Stefan Voß ,&nbsp;Mohammed EL Amrani","doi":"10.1016/j.jpubtr.2025.100124","DOIUrl":"10.1016/j.jpubtr.2025.100124","url":null,"abstract":"<div><div>The utilization of public transport data has evolved rapidly in recent decades. Ferries, with their unique characteristics and sensitivity to weather conditions, pose significant challenges for delay prediction. Given their pivotal role in the transportation systems of numerous cities, accurately predicting ferry delays is crucial for synchronizing transit services.</div><div>This paper demonstrates the value of open data for improving ferry delay predictions through machine learning, focusing on two case studies. Our approach leverages General Transit Feed Specification (GTFS) data, ridership and vessel information, and hourly weather data, combined with SHAP explainable artificial intelligence analysis to assess key delay determinants. While support vector regression and deep neural networks showed high accuracy in individual case studies, gradient boosting consistently offered the best balance between prediction accuracy and computational efficiency. Moreover, SHAP analysis reveals that operational and temporal features – such as stop sequence, trip start time, headway, and vehicle label – are the dominant drivers of delays, with weather-related factors exerting only a modest influence.</div></div>","PeriodicalId":47173,"journal":{"name":"Journal of Public Transportation","volume":"27 ","pages":"Article 100124"},"PeriodicalIF":2.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}