Identifying Ridesharing Risk, Response, and Challenges in the Emergence of Novel Coronavirus Using Interactions in Uber Drivers Forum

Mojumder, Md Nizamul Hoque; Ahmed, Md Ashraf; Sadri, Arif Mohaimin · 2021 · Crossref

DOI: 10.3389/fbuil.2021.619283

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study investigates the risks, responses, and challenges faced by ridesharing drivers and passengers during the early stages of the COVID-19 pandemic. Motivated by the unprecedented lockdowns and economic disruptions that severely impacted Transportation Network Companies (TNCs) like Uber and Lyft, the authors sought to understand how self-employed drivers perceived and managed risks associated with shared travel. With millions of drivers filing for unemployment and facing health hazards from asymptomatic passengers, the research aimed to identify unobserved factors affecting TNC operations and user behavior through the analysis of online social interactions. The researchers employed a text-mining approach using large-scale crowdsourced data collected from the "Uber Drivers Forum" between January 25 and May 10, 2020. The dataset comprised 29,773 texts extracted from three specific subforums: "Corona," "Lyft," and "Advice." To analyze this unstructured data, the authors utilized natural language processing techniques, including word frequency analysis, temporal heatmaps, word bigram analysis, and Latent Dirichlet Allocation (LDA) topic modeling. These methods were used to preprocess the text and classify behaviors related to risk perception, risk-taking, and risk-aversion. The results revealed distinct themes across the forums. In the "Corona" forum, discussions centered on health concerns, with high frequencies of words related to the virus, death tolls, and symptoms, alongside significant anxiety regarding economic disruption, unemployment, and government responses. The "Lyft" forum highlighted operational challenges, with frequent mentions of ride availability, payment issues, and passenger interactions. The "Advice" forum reflected broader economic struggles, with drivers discussing unemployment benefits, stimulus checks, and the decision to return to work despite health risks. Topic modeling further identified clusters related to personal hygiene, protective equipment, and the uncertainty of the "new normal." The study concludes that text-based analytics of online forums can effectively uncover the hidden dynamics of risk communication during crises. By identifying specific concerns such as economic instability and health safety, the findings provide insights for designing more efficient online social interaction outlets. The authors suggest that leveraging these platforms can help disseminate real-time guidelines to minimize disease transmission and support drivers and passengers in navigating the challenges of shared mobility during pandemics. This approach offers a framework for understanding user-centric risk information dissemination in future emergency situations.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• passenger effects