Abstract
In this study, app store reviews from two major micromobility companies are investigated using machine learning techniques to identify the factors that influence rider satisfaction. The Latent Dirichlet Allocation model is applied to over 12,000 rider-generated reviews to identify twelve topics discussed within the reviews. These topics cover areas such as pricing, safety, customer service, map, refund, payment, app interface, and ease of use, to name a few. Using logistic regression, the most significant factors influencing rider satisfaction were identified. Moreover, name-centered gender prediction analysis is employed to identify rider gender and then discover differences in review content and factors of satisfaction across gender. Results suggest rider satisfaction levels tend to vary across topics and gender. Women were more satisfied with the services and exhibited more positive sentiment than men. Yet, scooter is still a male dominated mode of transportation. Findings contribute to the existing literature by demonstrating the use of app store reviews in a transportation mobility study. The development of a method to assess factors contributing to rider satisfaction offers the ability to evaluate e-scooter rider needs and barriers. An apparent policy opportunity to increase scooter ridership includes an emphasis on contributing factors such as ease of use, safety (speed and riding lane), as well as app issues that showed significant influence on user satisfaction. It is recommended that a policy approach focused on improving rider satisfaction and delivering service improvements incorporate opinion mining as a methodology.
Original language | English (US) |
---|---|
Article number | 102856 |
Journal | Transportation Research Part D: Transport and Environment |
Volume | 95 |
DOIs | |
State | Published - Jun 2021 |
All Science Journal Classification (ASJC) codes
- Civil and Structural Engineering
- Transportation
- General Environmental Science
Keywords
- App store review
- Rider satisfaction
- Shared electric scooter
- Text mining
- Topic modeling