Abstract

Recommender systems assist users in finding relevant entities, such as books or movies, according to their individual preferences. The entities' properties along with their relationships have to be considered in order to articulate good recommendations. In this paper, we present an approach for developing an adaptive hybrid recommender system with semantic data. Such data is represented as large graph of nodes (semantic entities) and edges (semantic relations) filled with contents collected from Linked-Open-Data sources, such as the Internet Movie Database (IMDb) and Freebase. The system implements different algorithms to generate recommendations supporting the user in finding relevant, but potentially unknown movies. The system provides users with explicit explanations helping them to understand why a movie is relevant and to refine the request criteria according to their individual preferences. The system considers run-time complexity to guarantee a short request response time for individually adapted requests.

@inproceedings{LommatzschKilleKimAlbayrak:RecommenderForHeterogeneousSemanticData,
author = {Andreas Lommatzsch and Benjamin Kille and Jae Won Kim and Sahin Albayrak},
title = {An Adaptive Hybrid Movie Recommender based on Semantic Data},
booktitle = {Proceedings of the 10th Conference on Open Research Areas in Information Retrieval, OAIR 2013},
year = {2013},
series = {OAIR '13},
pages = {217--218},
numpages = {2},
isbn = {978-2-905450-09-8},
location = {Lisbon, Portugal},
url = {http://dl.acm.org/citation.cfm?id=2491748.2491795},
acmid = {2491795},
publisher = {LE CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE},
address = {Paris, France, France},
keywords = {content-based filtering, personalization, recommender systems, semantic data},
}