Learning Hybrid Recommender Models for Heterogeneous Semantic Data


Recommender algorithms are key technologies supporting users to deal with information overload. Recommender Systems (RS) aim at identifying relevant items a user is unaware of. The relevance of items depends on various criteria such as item properties, the relationship to other items, user preferences, and contexts. The aggregation of different criteria is the key in computing high-quality recommendations. We propose a novel approach for automatically learning parameters for recommendations based on semantic datasets (graphs). We outline how scaling models and noise reduction models allow us to consider individual dataset properties. We evaluated the proposed methods on a semantic movie data set. The evaluation shows that each semantic relationship set requires a separate recommender model. Combining such recommender models yields much higher precision. We show the recommender ensembles outperform recommenders based on aggregated semantic graphs (block matrix recommender).

author = {Andreas Lommatzsch and Benjamin Kille and Sahin Albayrak},
title = {Learning Hybrid Recommender Models for Heterogeneous Semantic Data},
booktitle = {Proc. of the 28th Symposium On Applied Computing, SAC 2013},
year = {2013},
series = {SAC '13},
pages = {275--276},
isbn = {978-1-4503-1656-9},
location = {Coimbra, Portugal},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Recommender Systems, Block Matrices, Ensembles, Semantic, Graphs},
Conference Paper
ACM SAC'13, March 18-22, 2013, Coimbra, Portugal