An adaptive neuro-fuzzy inference system for a location based social network

Abstract

Location Based Social Networks (LSBNs) has started with broadcasting the location via text messages long before the mobile applications and mobile data. Due to the technological developments, a notable number of technologies we use today are location-aware, and they are available to more people. When one of the most popular LSBN, Foursquare, has brought together both motivation of gameplay and social networks, and it introduced a new business model to the market. They have used points and badges to motivate users for “checking in” to locations. After that point, LSBNs started to be a useful tool that effected purchase decision and became vital for information research, evaluation of alternatives and post-purchase evaluation. Typically, the score of the venues is a significant decision-making parameter for most of the users for a purchase decision. Due to the complex and undisclosed score calculation method of Foursquare, it has been a wonder to users and venue owners. Purpose of the research is to build a model that can predict venue scores based on variables such as check-in counts, review, tip and photo counts of venues.