 Discovering latent topics and trends in autonomous vehicle-related research: A structural topic modelling approachReuben Tamakloe and Dongjoo Park Transport Policy, 2023, vol. 139, issue C, 1-20 Abstract: Autonomous Vehicle (AV) technology is a disruptive transportation technology that promises to revolutionize how people travel. Due to their potential mobility benefits and associated impacts on public health and the environment, they have received massive attention from transportation experts. To date, there have been numerous academic research conducted regarding AVs, and many attempts have been made to summarize these research documents by manually reviewing them. Nevertheless, due to the vast nature of the existing literature, it is challenging to synthesize the themes in AV-related research and to explore their trends to inform future research direction. This study aims to utilize an advanced natural language processing technique to provide a comprehensive overview of the recent developments in AV-related research. The abstracts of 3292 articles published in transportation-based journals from January 2016 to October 2022 were collected and used for this study. A Structural Topic Model (STM) was employed to explore the dominant research themes hidden in the extant literature on AV research, examine their evolution over time, and determine the topics highly associated with developing and developed economies. Overall, the study highlighted that the least common themes in the literature are in the areas of the development of complex vehicle designs, safety, environmental benefits, and the impact of AVs on transportation infrastructure. Nevertheless, themes concerning AV safety and the environment are emerging as hot topics since late 2021. Topics related to investigating user perceptions, policies/approaches to increase user demand, and AV control/stability are highly studied. Besides, they predominantly originated from developed countries. The research themes, their associated trends, and the key policy suggestions drawn from the study are potentially useful for making well-informed research funding decisions, setting research priorities for countries, and guiding the future research endeavours of researchers. Keywords: Autonomous vehicle; Transportation; Environment; Structural topic model; Machine learning; Transport policy (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:eee:trapol:v:139:y:2023:i:c:p:1-20 Ordering information: This journal article can be ordered from DOI: 10.1016/j.tranpol.2023.06.001 Access Statistics for this article Transport Policy is currently edited by Y. Hayashi More articles in Transport Policy from Elsevier |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.