Measurement And Analysis Of Tips In Foursquare

Being a leading online service providing both local search and social networking functions, Foursquare has attracted tens of millions of users all over the world. As a location-centric platform, Foursquare maintains the information of numerous venues, and it has recorded a tremendous amount of users' tips for these venues. Tips (micro-reviews) play a critical role in helping users find a good venue and providing comments for the venue owners. A lot of studies have been done in investigating social connections and check-in patterns among Foursquare users. However, there is a lack of a thorough study on tips, the primary type of user-generated contents (UGCs) in Foursquare. In this paper, by crawling and analyzing all tips published by more than 6 million users, we study Foursquare's tips from various aspects. We start from counting the number of tips published by different users and conduct a group-based analysis of the average number of published tips per user. Moreover, we look into the important fields of tips. We study the venue category distribution, and the evolution of the number and diversity of tips. Finally, we conduct a series of sentiment analysis by referring to the texts of all tips and introduce the concept of happiness index to evaluate the overall level of satisfaction of a set of tips. To the best of our knowledge, our study presents the first comprehensive and unbiased picture of tips in Foursquare.