Content-Based Top-N Recommendation using Heterogeneous Relations
This work addresses cold-start and sparsity issues in recommender systems, but it is incremental as it builds on existing hybrid approaches with a focus on leveraging profile information.
The paper tackles the sparsity and cold-start problems in top-N recommender systems by proposing a content-based method that learns global term weights from profiles using PathSim to handle heterogeneous relations, achieving superior performance in experiments.
Top-$N$ recommender systems have been extensively studied. However, the sparsity of user-item activities has not been well resolved. While many hybrid systems were proposed to address the cold-start problem, the profile information has not been sufficiently leveraged. Furthermore, the heterogeneity of profiles between users and items intensifies the challenge. In this paper, we propose a content-based top-$N$ recommender system by learning the global term weights in profiles. To achieve this, we bring in PathSim, which could well measures the node similarity with heterogeneous relations (between users and items). Starting from the original TF-IDF value, the global term weights gradually converge, and eventually reflect both profile and activity information. To facilitate training, the derivative is reformulated into matrix form, which could easily be paralleled. We conduct extensive experiments, which demonstrate the superiority of the proposed method.