Utilizing Social Media Data for Estimating Transit Performance Metrics

Abstract

In this paper, a methodology using text and sentiment analysis of social media data is proposed to determine performance metrics that customers frequently mentioned when riding the New York Transit system and how they compare to those reported by the transit agency. This method is carried out by analyzing Twitter data collected from users mentioning their transit experience and recognizing trends regarding sentiment. The results show that customers mostly express negative over positive experiences about their transit services in terms of perceptions and expectations. Transit users are more critical about wait times and delays and notice the positive factors during service, such as system aesthetics, train speed, station cleanliness, and safety (in that order). The data analyzed also provides insights on locations and transit lines where there are frequent occurrences of customer issues. The proposed methodology provides a relevant contribution from a practical viewpoint because performance metrics are important factors to consider by transit operators which are exploring new practices to retain and attract ridership, given that transit systems are generally considered among the sustainable modes of transportation.