Content based News Recommendation via Shortest Entity Distance over Knowledge Graphs

TL;DR

This paper introduces a graph traversal algorithm that uses shortest entity distances over knowledge graphs to improve cold-start content-based news recommendation, demonstrating better correlation with human judgments.

Contribution

It proposes a novel shortest entity distance algorithm and weighting scheme for cold-start news recommendation using knowledge graphs, along with a new annotated dataset for evaluation.

Findings

Outperforms existing cold-start recommendation methods in correlation with human similarity scores

Effective in addressing the cold-start problem in news recommendation

Combines well with traditional methods for enhanced performance

Abstract

Content-based news recommendation systems need to recommend news articles based on the topics and content of articles without using user specific information. Many news articles describe the occurrence of specific events and named entities including people, places or objects. In this paper, we propose a graph traversal algorithm as well as a novel weighting scheme for cold-start content based news recommendation utilizing these named entities. Seeking to create a higher degree of user-specific relevance, our algorithm computes the shortest distance between named entities, across news articles, over a large knowledge graph. Moreover, we have created a new human annotated data set for evaluating content based news recommendation systems. Experimental results show our method is suitable to tackle the hard cold-start problem and it produces stronger Pearson correlation to human similarity scores than other cold-start methods. Our method is also complementary and a combination with the conventional cold-start recommendation methods may yield significant performance gains. The dataset, CNRec, is available at: https://github.com/kevinj22/CNRec