Abstract

Context-aware recommender systems are becoming a popular topic, still, there are many untouched aspects. In this paper, research involving context identification and the concepts related to hybrid and context-aware systems is presented. A conceptual architecture for a context-aware recommender system for movies and TV shows is furthermore introduced. The system consists of a number of processes for context identification and recommendation. Key contextual features are identified and used for the creation of several sets of recommendations, based on the predicted context. The main focus of the research presented here is the identification of context, which in turn is used for recommendation. The results will be evaluated and incorporated into the recommendation engine of movie and TV recommendation website Moviepilot.

@inproceedings{said2010b,
author = {Alan Said},
title = {Identifying and Utilizing Contextual Data in Hybrid Recommender Systems},
booktitle = {RecSys 2010: Proceedings of the fourth ACM conference on Recommender systems},
year = {2010},
location = {Barcelona, Spain},
publisher = {ACM},
address = {New York, NY, USA},
}