Abstract
How does ChatGPT introduce transport problems and solutions in North America? By analyzing ChatGPT’s answers to four prompts related to transport issues and solutions in the United States and Canada, our results reveal that ChatGPT’s answers generally align well with transport researchers’ expectations. However, ChatGPT’s capability may be limited in providing trustworthy or sound solutions because of the potential issues (e.g., geographic biases, inaccuracy) in its training data. ChatGPT might be a decent starting point for discussing transport issues and solutions, but one should be aware of its limitations.
Publisher
Network Design Lab - Transport Findings
Reference11 articles.
1. Uneven geographies of user-generated information: Patterns of increasing informational poverty;Mark Graham;Annals of the Association of American Geographers,2014
2. The evolution of Health & Place: Text mining papers published between 1995 and 2018;Mark A. Green;Health & Place,2020
3. The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation;J. Hartmann;arXiv preprint,2023
4. Global Traffic Scorecard;INRIX,2022
5. Quantitative Geographical Approaches in COVID-19 Research: A Review on First- and Second-Order Impacts;Junghwan Kim;The Geographies of COVID-19,2022
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献