Exploiting hierarchical tags for context-awareness.

ABSTRACTContext-awareness for information retrieval is a challenging problem as information about the user's current situation is rarely available. However, if such information is available, retrieval and recommendation systems could use it to find information more relevant to their users' current context. We present a model for creating contextualized recommendations based on implicitly expressed context via keywords assigned to previously seen items and other available information. When employed, the model can create ad hoc recommendation with improved accuracy.