SNA-Based Recommendation in Professional Learning Environments

Recommender systems can provide effective means to support self-organization and networking in professional learning environments. In this paper, we leverage social network analysis (SNA) methods to improve interest-based recommendation in professional learning networks. We discuss two approaches for interest-based recommendation using SNA and compare them with conventional collaborative filtering (CF)-based recommendation methods. The user evaluation results based on the ResQue framework confirm that SNA-based CF recommendation outperform traditional CF methods in terms of coverage and thus can provide an effective solution to the sparsity and cold start problems in recommender systems.