Solving the Cold-Start Problem in Recommender Systems with Social Tags

TL;DR

This paper introduces a social tag-based recommendation algorithm that improves accuracy and diversity, especially for cold-start items, by leveraging user-tag-object tripartite graphs in social tagging systems.

Contribution

It proposes a novel algorithm utilizing social tags and tripartite graphs to address cold-start issues and enhance recommendation quality in social tagging systems.

Findings

Improves recommendation accuracy and diversity.

Effective for small degree objects and cold-start items.

Significantly solves the cold-start problem in social tagging systems.

Abstract

In this paper, based on the user-tag-object tripartite graphs, we propose a recommendation algorithm, which considers social tags as an important role for information retrieval. Besides its low cost of computational time, the experiment results of two real-world data sets, \emph{Del.icio.us} and \emph{MovieLens}, show it can enhance the algorithmic accuracy and diversity. Especially, it can obtain more personalized recommendation results when users have diverse topics of tags. In addition, the numerical results on the dependence of algorithmic accuracy indicates that the proposed algorithm is particularly effective for small degree objects, which reminds us of the well-known \emph{cold-start} problem in recommender systems. Further empirical study shows that the proposed algorithm can significantly solve this problem in social tagging systems with heterogeneous object degree distributions.