AI Companions in Ride-Hailing: Enhancing Sense of Safety with Voice Chatbots
DOI:
https://doi.org/10.47756/aihc.y9i1.138Keywords:
People’s safety, Ride-hailing, Large Language Models, System Evaluation, Voice chat bot, Artificial IntelligenceAbstract
In this paper, we present the development and formative evaluation of AI Companion, a voice chatbot based on Artificial Intelligence Large Language Models designed to enhance users' perception of safety and control during transportation using ride-hailing apps or similar services. We conducted a study with 10 participants to understand their travel experiences and evaluate the AI Companion's ability to maintain coherent conversations, simulating a phone call. Our findings indicate that participants generally liked the system. However, we provide several recommendations for significant improvements to the AI Companion.
Downloads
References
N. Gardner, J. Cui, and E. Coiacetto, “Harassment on public transport and its impacts on women’s travel behaviour,” Australian Planner, vol. 54, no. 1, pp. 8–15, Jan. 2017, doi: 10.1080/07293682.2017.1299189. DOI: https://doi.org/10.1080/07293682.2017.1299189
B. Chaudhry, A. U. H. Yasar, S. El-Amine, and E. Shakshuki, “Passenger Safety in Ride-Sharing Services,” in Procedia Computer Science, Elsevier B.V., 2018, pp. 1044–1050. doi: 10.1016/j.procs.2018.04.146. DOI: https://doi.org/10.1016/j.procs.2018.04.146
S. Hu and Y. Yang, “Safety of female ride-hailing passengers: Perception and prevention,” Humanit Soc Sci Commun, vol. 11, no. 1, Dec. 2024, doi: 10.1057/s41599-024-02740-z. DOI: https://doi.org/10.1057/s41599-024-02740-z
K. M. Cumiskey, “Simply Leaving My House Would Even Be Scarier’: How Mobile Phones Affect Women’s Perception of Safety and Experiences of Public Places,” Media Asia, vol. 37, no. 4, pp. 205–214, 2010.
M. Schuß, C. Manger, A. Löcken, and A. Riener, “You’ll Never Ride Alone: Insights into Women’s Security Needs in Shared Automated Vehicles,” in Main Proceedings - 14th International ACM Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI 2022, Association for Computing Machinery, Inc, Sep. 2022, pp. 13–23. doi: 10.1145/3543174.3546848. DOI: https://doi.org/10.1145/3543174.3546848
M. S. Farooq, A. Masooma, U. Omer, R. Tehseen, S. A. M. Gilani, and Z. Atal, “The Role of IoT in Woman’s Safety: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 69807–69825, 2023, doi: 10.1109/ACCESS.2023.3252903. DOI: https://doi.org/10.1109/ACCESS.2023.3252903
M. Osipova and E. Hornecker, “Exploring the potential for Smart City technology for Women’s Safety,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Oct. 2023, pp. 245–256. doi: 10.1145/3616961.3616988. DOI: https://doi.org/10.1145/3616961.3616988
T. Wu et al., “A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development,” IEEE/CAA Journal of Automatica Sinica, vol. 10, no. 5, pp. 1122–1136, May 2023, doi: 10.1109/JAS.2023.123618. DOI: https://doi.org/10.1109/JAS.2023.123618
S. C. Peres, “The Effect of Experience on System Usability Scale Ratings,” 2011. [Online]. Available: https://www.researchgate.net/publication/267411691
D. Banik, N. Pati, and A. Sharma, “Systematic exploration and in-depth analysis of ChatGPT architectures progression,” Artif Intell Rev, vol. 57, no. 9, Sep. 2024, doi: 10.1007/s10462-024-10832-0. DOI: https://doi.org/10.1007/s10462-024-10832-0
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
AMexIHC make every effort to ensure the accuracy and rigour of all the information (the "Content") contained in out publications. However, AMexIHC and our representatives make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by AMexIHC. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information.