Deriving Knowledge Profiles from Twitter

E-learning systems often include a personalization component, which adapts the learning content to the learner’s particular needs. One obstacle to personalization is the question of how to obtain a learner profile for a learner who just starts using an E-learning system without overwhelming her with questions or unsuitable learning material. One possible solution to this problem lies in the social Web. If a learner is active on the social Web, a considerable amount of information about her is already available. Depending on the social Web service(s) the learner uses, her tweets, photos, bookmarks, etc. are publicly accessible. We investigate if it is feasible to exploit the social Web, more specifically the social Web service Twitter, to infer a learner’s knowledge profile in order to overcome the “cold-start” problem in E-learning systems.