Heterogeneous Collaborative Filtering
This addresses recommendation system challenges for content sharing/creating social networks, but appears incremental as it builds on existing collaborative filtering methods.
The authors tackled the cold start problem and narrow content diversity in conventional collaborative filtering by proposing heterogeneous collaborative filtering (HCF), which improved recommendation quality in a real-world social network.
Recommendation system is important to a content sharing/creating social network. Collaborative filtering is a widely-adopted technology in conventional recommenders, which is based on similarity between positively engaged content items involving the same users. Conventional collaborative filtering (CCF) suffers from cold start problem and narrow content diversity. We propose a new recommendation approach, heterogeneous collaborative filtering (HCF) to tackle these challenges at the root, while keeping the strength of collaborative filtering. We present two implementation algorithms of HCF for content recommendation and content dissemination. Experiment results demonstrate that our approach improve the recommendation quality in a real world social network for content creating and sharing.