Taxi Driving Behavior Analysis in Latent Vehicle-to-Vehicle Networks: A Social Influence Perspective
Tong Xu*, USTC; Hengshu Zhu, Baidu Inc.; Xiangyu Zhao, USTC; Hao Zhong, Rutgers University; Qi Liu, University of Science and Technology of China; Enhong Chen, ; Hui Xiong, Rutgers
With recent advances in mobile and sensor technologies, a large amount of eﬀorts have been made on developing intelligent applications for taxi drivers, which provide beneﬁcial guide and opportunity to improve the proﬁt and work eﬃciency. However, limited scopes focus on the latent social interaction within cab drivers, and corresponding social propagation scheme to share driving behaviors has been largely ignored. To that end, in this paper, we propose a comprehensive study to reveal how the social propagation aﬀects for better prediction of cab drivers’ future behaviors. To be speciﬁc, we ﬁrst investigate the correlation between drivers’ skills and their mutual interactions in the latent vehicle-to-vehicle network, which intuitively indicates the eﬀects of social inﬂuences. Along this line, by leveraging the classic social inﬂuence theory, we develop a two-stage framework for quantitatively revealing the latent driving pattern propagation within taxi drivers. Comprehensive experiments on a real-word data set collected from the New York City clearly validate the eﬀectiveness of our proposed framework on predicting future taxi driving behaviors, which also support the hypothesis that social factors indeed improve the predictability of driving behaviors.