Enriching lifelong user modelling in a social networking and e-commerce era

Lifelong User Modelling is an area that aims at harvesting the massive volume of web-based user information, so that it can be used for educational long-term services. Although an amount of research has addressed this issue from an educational angle, by finding ways for educational peer systems to exchange data sets among them, little has been done to investigate the potential of the social networking and e-commerce domains in the Lifelong User Modelling vision to enable Lifelong Learning services to be used. This thesis presents a Scrutable User Modelling Infrastructure (SUMI) that can accommodate current social networking and e-commerce services for allowing the exchange of user data among these services and educational systems, for potentially improved personalisation services. Special focus has been given to three user modelling aspects: interoperability, scrutability and privacy. The suitability of SUMI regarding these aspects is tested by developing and evaluating a prototype service. The prototype SUMI service focuses on making the infrastructure scrutable, in terms of allowing users to have control of their imported models in SUMI, while also offering various controls for safeguarding the privacy of their information in SUMI. To assess our interoperability design decisions, four successful simulation tests have been conducted. To evaluate the proposed scrutability and privacy user privileges, two user-based evaluations have been carried out. For each evaluation, the method and results are described. Overall results have revealed that participants have expressed their general acceptance of having available such an infrastructure and service, while favouring a more holistic approach when exposed to such an environment.