Location-based social networks (LBSNs) are rich sources of studying travel mobility of people. With more users sharing updates about their activities in LBSNs, there is availability of enough data to learn about their travel mobility patterns (TMPs). Design of destination recommender systems (DRSs), in turn, can benefit from better understanding of travellers’ mobility patterns. We research on wide-range literature in the field of TMPs and DRSs, and also discover no such system that recommends personalised city trips to different users by employing data-driven approaches. In this thesis, we study the TMPs of people using trips extracted from Twitter check-ins and design a DRS that computes personalised city trips for users based on their travel preferences. We come up with 10 prototype traveller types, having similar and dissimilar features with each other. We also divide the world into 10 regions, and segregate 93, 955 trips based on the home regions of travellers. The partitioned trips are then clustered, which in turn, also group the travellers around the world, conforming to the previously modelled traveller types. Finally, we develop a prototype web application, TripRec to test the functionalities of our algorithm that recommends destinations from a set of 138 cities in the database. The application accepts user information and preferences like home region, destination region, traveller type, maximum travel duration and fondness for different types of venues in a city, as inputs. Satisfying the user preferences and constraints, a suitable trip including an ordered list of cities with duration of stay at each is determined, to be recommended to the user. This thesis, thus, reveals a novel data-driven approach to build a recommender system application for planning composite city trips, personalised to user requirements.     «

Location-based social networks (LBSNs) are rich sources of studying travel mobility of people. With more users sharing updates about their activities in LBSNs, there is availability of enough data to learn about their travel mobility patterns (TMPs). Design of destination recommender systems (DRSs), in turn, can benefit from better understanding of travellers’ mobility patterns. We research on wide-range literature in the field of TMPs and DRSs, and also discover no such system that recommends p...     »

Location-based social networks (LBSNs) are rich sources of studying travel mobility of people. With more users sharing updates about their activities in LBSNs, there is availability of enough data to learn about their travel mobility patterns (TMPs). Design of destination recommender systems (DRSs), in turn, can benefit from better understanding of travellers’ mobility patterns. We research on wide-range literature in the field of TMPs and DRSs, and also discover no such system that recommends personalised city trips to different users by employing data-driven approaches. In this thesis, we study the TMPs of people using trips extracted from Twitter check-ins and design a DRS that computes personalised city trips for users based on their travel preferences. We come up with 10 prototype traveller types, having similar and dissimilar features with each other. We also divide the world into 10 regions, and segregate 93, 955 trips based on the home regions of travellers. The partitioned trips are then clustered, which in turn, also group the travellers around the world, conforming to the previously modelled traveller types. Finally, we develop a prototype web application, TripRec to test the functionalities of our algorithm that recommends destinations from a set of 138 cities in the database. The application accepts user information and preferences like home region, destination region, traveller type, maximum travel duration and fondness for different types of venues in a city, as inputs. Satisfying the user preferences and constraints, a suitable trip including an ordered list of cities with duration of stay at each is determined, to be recommended to the user. This thesis, thus, reveals a novel data-driven approach to build a recommender system application for planning composite city trips, personalised to user requirements.     «

Location-based social networks (LBSNs) are rich sources of studying travel mobility of people. With more users sharing updates about their activities in LBSNs, there is availability of enough data to learn about their travel mobility patterns (TMPs). Design of destination recommender systems (DRSs), in turn, can benefit from better understanding of travellers’ mobility patterns. We research on wide-range literature in the field of TMPs and DRSs, and also discover no such system that recommends p...     »