Social-Aware Ridesharing in Location-Based Services

With the deep penetration of smartphones and geo-locating devices, ridesharing is envisioned as a promising solution to mitigate transportation-related problems such as congestion and air pollution for metropolitan cities like Hong Kong. As reported in a recent study, 1 the potential reduction of urban traffic can be as high as 31-59% if individuals with similar travel itineraries and schedules are willing to share a ride. However, despite the potential to provide significant societal and environmental benefits, ridesharing has not so far been as popular as expected. Notable barriers include social discomfort and safety concerns about traveling with strangers. To overcome these barriers, in this project we propose social-aware ridesharing services, whereby participants’ social connections are considered besides spatio-temporal proximity in assigning them to shared rides.

The development of rideshare assignment algorithms is central to the success of ridesharing services. Though they have been studied extensively in the literature, little work has been carried out in terms of social-aware ridesharing. The consideration of social factors in ridesharing introduces several new challenges. First, a fundamental issue is how to capture and model social constraints for effective ridesharing. Second, social relationships touch upon network graph structures and may not preserve the locality property (e.g., a 2-core network may no longer hold after adding/removing some participants). As such, the social-aware rideshare assignment problem becomes more complex and new algorithms must be designed to support efficient query processing. To address these challenges, our research agenda for this project is planned as follows: 1) the modeling of social constraints that can improve trust among rideshare participants while keeping rideshare assignments flexible; 2) the design of efficient ride assignment algorithms for both instant and batch social-aware ridesharing problems; 3) the performance evaluation of the proposed algorithms and assessment of the potential of social-aware ridesharing to reduce traffic and save energy with real trajectory and social network data; 4) the development of a prototype system to demonstrate the feasibility of our proposals.

With our extensive research experience in spatial query processing and location-aware computing, we hope the outcome of this project will lead to an increase in the adoption of ridesharing services and as a result benefit both individuals and society as a whole.