This thesis carried out two major investigations on how the geographical information generated by users in social media can be used to model and predict human behaviours. The first investigation regards the mobility patterns of social media users, which utilizes the relations between geographical information and other sources of information, e.g., textual information and temporal information (Chapter 3) as well as users' trajectory patterns, in predicting the locations of users' future visits (Chapter 4). The experimental results confirm the predictability of human movement and the proposed methods for predicting users' locations are demonstrated to outperform the state-of-the-art via evaluations with the data collected from social media platforms (Twitter and Foursquare). The second investigation regards the geo-knowledge that users may gain from physical visits to locations (Chapter 5). The thesis first presented a discussion on how such knowledge can be modelled from users' check-in posts on social media and then approached this problem from both theoretical and practical points of view. Probabilistic models were built and tested via a configurable system on which all the models were implemented. To evaluate the proposed models, a data set of ground truth was collected by annotation from two different sources (i.e., a crowdsourcing platform and university students/staff). The evaluation show that the proposed models outperform the approaches from related research.
|Qualification||Doctor of Philosophy|
|Award date||23 May 2016|
|Publication status||Published - 2016|