Personalized tour recommendation using location-based social media

Tourism is a popular leisure activity and an important industry, where the main task involves visiting unfamiliar Places-of-Interest (POI) in foreign cities. Recommending POIs and tour planning are challenging and time-consuming tasks for tourists due to: (i) the need to identify and recommend captivating POIs in an unfamiliar city; (ii) having to schedule POI visits as a connected itinerary that satisfies trip constraints such as starting/ending near a specific location (e.g., the tourist’s hotel) and completing the itinerary within a limited touring duration; and (iii) having to satisfy the diverse interest preferences of each unique tourist. While tourism-related information can be obtained from the Internet, travel guides and tour agencies, many of these resources simply recommend individual POIs or popular itineraries, but otherwise do not appeal to the interest preferences of users or adhere to their trip constraints. In contrast to existing works on next-POI prediction and top-k POI recommendation that recommend a single POI or a ranked list of POIs, the task of tour recommendation involves the need to identify a set of interesting POIs and schedule them as an itinerary with various time and space constraints. While there are works on path planning that recommend an itinerary, this itinerary is typically optimized based on a global utility such as POI popularity, and thus offer no personalization for a tourist based on his/her interest preferences. This thesis addresses the challenges associated with the automation and personalization of tour recommendation using data mining techniques to model user interest and POI-related information, and using optimization problems and techniques to formulate and solve more realistic tour recommendation problems. Our main contributions include: