A Novel Transit Rider Satisfaction Metric: Rider Sentiments Measured from Online Social Media Data

The goal of this paper is to demonstrate the use of an innovative social media-based data source, Twitter, to evaluate transit rider satisfaction. Transit authorities have access to vast amounts of performance metrics that measure ridership, timeliness, efficiency, safety, cleanliness, and service, to name a few. These performance metrics, however, are generally one-sided; they represent the interests of the business and are not customer-based. This paper recognizes the limitations of standard performance metrics and attempts to gauge transit rider sentiments by measuring Twitter feeds. Sentiment analysis is used to classify a population of rider sentiments over a period of time. Conclusions are drawn from totals of positive and negative sentiments, normalized average sentiments, and the total number of Tweets collected over a time period. Introduction With the advent of social media, people are able to express their opinions on a subject instantaneously. Researchers are beginning to “mine” these opinions from social media outlets (i.e., Twitter, Facebook) to form general public perceptions, or sentiments, on a number of subjects. Sentiment analysis, or opinion mining, is the examination of a text through software to understand the positive or negative connotations surrounding it. Sentiment analysis can assist companies in determinJournal of Public Transportation, Vol. 16, No. 2, 2013 22 ing how a brand is perceived in relation to value and quality. Subtasks of sentiment analysis include determining subjectivity, polarity (positive or negative), and degree of polarity, and classifying the subject matter and author. Sentiment analysis, through the monitoring of social media, can change the way transit agencies measure rider satisfaction. For trips with similar distances, transit agencies are in direct competition with automobile services as well as pedestrian modes such as walking and bicycling. Commuters are likely to choose modes that maximize their utility and provide the most satisfaction (Andreassen 1995). Studies have been conducted that show commuters are more likely to choose modes that are more economical, comfortable, work-friendly, punctual, and safe (Hanna and Drea 1998). Thevathasan and Balachandran (2007) found that transit passengers consider improvements to safety and stations, improvements in facilities, and cleanliness to be important. Unfortunately for transit agencies, there is often a lack of compatibility between passenger needs and management perception of those needs. Management runs the risk of misallocating scarce resources and not being aware of growing passenger dissatisfaction with transit services that are measured by performance metrics (Koushki et al. 2003). Performance metrics are constructed to encourage performance improvement, effectiveness, efficiency, and appropriate levels of internal controls. Traditionally, performance metrics are measured through quantities related to ridership, timeliness, efficiency, safety, cleanliness, service, and courtesy (Chicago Transit Authority 2011; Metropolitan Transit Authority 2011). The Transit Capacity and Quality of Service Manual (TCQSM) (1999) recognizes that there is a distinct difference between transit agency and passenger point of view for quality of service. TCQSM indicates service coverage, hours of service, amenities, safety, and travel time as relevant to passengers, whereas annual ridership, vehicles operated in maximum service, passenger miles/revenue hour, and vehicle operating expenses are relevant to transit agencies. An analysis of Portland, Oregon’s, local transit provider (TriMet) shows how technology can be used to develop an archival system that directly relates bus transit performance to performance indicators through the use of its bus dispatch system (Bertiniand and El-Geneidy 2003). With the ever-growing complexities of urban transit and decreasing of federal and state funding, many transit authorities may not have the means to monitor zones with high amounts of activity. Through the use of online social media, commuters can voice their concerns in real time about current conditions in service, safety,