An entity graph based Recommender System

Sneha Chaudhari, Amos Azaria, Tom Mitchell

Research output: Contribution to journalArticlepeer-review


Recommender Systems have become increasingly important and are applied in an increasing number of domains. While common collaborative methods measure similarity between different users, common content based methods measure similarity between different content. We propose a privacy aware recommender system that exploits relations present between entities appearing in content from user's history and entities appearing in candidate content. In order to identify such relations, we use the knowledge graph of NELL, which encodes entities and their relations. We present a novel normalized version of Personalized PageRank, to rank candidate content. We test our approach on the movie recommendation domain and show that the proposed method outperforms other baseline methods, including the standard Personalized PageRank. We intend to deploy our recommender system as a news recommendation app for mobile devices.

Original languageEnglish
Pages (from-to)141-149
Number of pages9
JournalAI Communications
Issue number2
StatePublished - 2017

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence


Dive into the research topics of 'An entity graph based Recommender System'. Together they form a unique fingerprint.

Cite this