Document Type

Article

Publication Date

11-2025

Publication Title

Transportation Research Interdisciplinary Perspectives

Volume

34

Publisher

Elsevier

DOI

https://doi.org/10.1016/j.trip.2025.101765

Abstract

Social media provides a rich, alternative data source to interviews or survey-based research to study hard-to-reach populations (e.g., truck drivers, because of their transient work structure and unique subculture). This study uses public social media posts from the largest trucking forum in the United States to examine truck drivers’ views on autonomous trucks (ATs), which are poised to transform the trucking industry. We expand on traditional qualitative strategies of analyzing social media data by combining newer methods, including BERT-based topic modeling, sentiment analysis, stance detection, emotion analysis, topic similarity, and location analysis through a social interaction network, to analyze a large qualitative sample of social media posts (N = 4,245 posts from 1,319 users). Our BERT-based topic modeling results corroborated with research using traditional qualitative analytic approaches that drivers expressed a generally unfavorable view towards ATs, driven by a lack of trust in their feasibility and effective implementation, and concern for displacement. This study advances our current knowledge of truck drivers views of ATs by offering more comprehensive and nuanced insights enabled by novel combination of emerging methods for analyzing passive and active use of social media data, including sentiment analysis, stance detection, emotion analysis, and location analysis.

Comments

CC BY 4.0

Attribution 4.0 International

https://creativecommons.org/licenses/by/4.0/

Download

Share

COinS