Location

Grand Wailea, Hawaii

Event Website

https://hicss.hawaii.edu/

Start Date

7-1-2020 12:00 AM

End Date

10-1-2020 12:00 AM

Description

Trust is a key issue to be considered deliberately in the online ride-sharing platform to reduce risk and ensure transactions. In this paper, trust-in-platform is explored from these two perspectives to fill the research gaps. A ride-sharing platform in China was investigated. Results show that trust-in-platform in economically developing districts is slightly higher than that in economically developed districts. At the same time, trust-in-platform level differs in time, trust-in-platform levels are obviously lower between 19’o clock and 23’o clock. Moreover, machine learning is employed to predict the relationships between time/location and trust-in-platform. The result is that recall is 78.3%, precision is 57.3%, and F1 is 66.2%. The result shows trust-in-platform has an obvious correlation with time and location, thus further consolidates the findings. This study contributes to the existing knowledge on trust in the ride-sharing platforms and has practical implications for platform operators.

Share

COinS
 
Jan 7th, 12:00 AM Jan 10th, 12:00 AM

Exploring Trust in Online Ride-sharing Platform in China: A Perspective of Time and Location

Grand Wailea, Hawaii

Trust is a key issue to be considered deliberately in the online ride-sharing platform to reduce risk and ensure transactions. In this paper, trust-in-platform is explored from these two perspectives to fill the research gaps. A ride-sharing platform in China was investigated. Results show that trust-in-platform in economically developing districts is slightly higher than that in economically developed districts. At the same time, trust-in-platform level differs in time, trust-in-platform levels are obviously lower between 19’o clock and 23’o clock. Moreover, machine learning is employed to predict the relationships between time/location and trust-in-platform. The result is that recall is 78.3%, precision is 57.3%, and F1 is 66.2%. The result shows trust-in-platform has an obvious correlation with time and location, thus further consolidates the findings. This study contributes to the existing knowledge on trust in the ride-sharing platforms and has practical implications for platform operators.

https://aisel.aisnet.org/hicss-53/cl/it_enabled_collaboration/2