Evaluating collaborative filtering recommender systems
ACM Transactions on Information Systems (TOIS)
IEEE Transactions on Knowledge and Data Engineering
TANGENT: a novel, 'Surprise me', recommendation algorithm
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Collaborative filtering recommender systems
The adaptive web
Content-based recommendation systems
The adaptive web
Beyond accuracy: evaluating recommender systems by coverage and serendipity
Proceedings of the fourth ACM conference on Recommender systems
Hi-index | 0.00 |
In this paper an approach to serendipitous item recommendation is outlined. The model used for this task is an extension of ProfileMatcher, which is based on fuzzy metadata describing both user and items to be recommended. To address the task of recommending serendipitous resources, a priori knowledge on the relations occurring among metadata values is injected in the recommendation process. This is achieved using fuzzy graphs to model similarity relations among the elements of the fuzzy sets describing the metadata. An experimentation has been carried out on the MovieLens data set to show the impact of serendipity injection in the item recommendation process.