Visual Twitter Analytics: Exploring Fan and Organizer Sentiment During Le Tour de France

In recent years, Twitter has become a valuable source of information regarding the public perception of products, services, and events. Not only have many sport organizations embraced Twitter as a communication mechanism, the public and collaborative nature of Twitter has allowed fans to communicate with and respond to the organizers, as well as with one another. As a result, Twitter represents a vast wealth of information for understanding fan and sport organization behaviour. However, analyzing such data for the purposes of sport management research is difficult due to the size, temporality, and textual nature of the data. In this paper, we present a visual analytics approach to analyzing the temporally changing sentiment within Twitter, called Vista. Machine learning is used to extract sentiment from individual tweets, which are visually represented using a timeline; interactive tools support exploration and analytical reasoning about the data. A case study is provided to illustrate the types of analyses that can be performed with Vista.