Bridging the gap between linked open data-based recommender systems and distributed representations
作者：
Highlights：
• We introduce Linked Open Data (LOD) into a content-based recommender system.
• LOD are used to enrich the representation of items by leveraging RDF statements.
• LOD are introduced through holographic embeddings of knowledge graphs built from Wikidata.
• Evaluation performed on three standard datasets: Movielens 1M, Last.fm and LibraryThing.
• The experimental results are promising and confirm the effectiveness of the proposed method.
摘要
•We introduce Linked Open Data (LOD) into a content-based recommender system.•LOD are used to enrich the representation of items by leveraging RDF statements.•LOD are introduced through holographic embeddings of knowledge graphs built from Wikidata.•Evaluation performed on three standard datasets: Movielens 1M, Last.fm and LibraryThing.•The experimental results are promising and confirm the effectiveness of the proposed method.
论文关键词：Recommender systems,Knowledge graph embedding,Linked data
论文评审过程：Received 8 May 2018, Accepted 1 July 2019, Available online 3 July 2019, Version of Record 8 July 2019.
论文官网地址：https://doi.org/10.1016/j.is.2019.07.001
