HAR-SI: A novel hybrid article recommendation approach integrating with social information in scientific social network.

With the rapid development of information technology, scientific social network, i.e. SSN, have become the fastest and most convenient way for researchers to communicate with each other. However, a lot of published articles are shared via SSN every day which make it difficult for researchers to find highly valuable articles. To solve above information overload problem, a novel hybrid approach integrating with social information, i.e., HAR-SI, is proposed for the article recommendation in SSN. Unlike the traditional CBF and CF recommendation approaches, the social tag information and social friend information, which have been proved playing a significant role on recommendation in many domains, are effectively integrated into these two approaches separately to improve the accuracy in SSN. Prediction results made by the improved CBF and CF separately are combined with a hybrid method. In order to verify the effectiveness of the proposed HAR-SI, a real-life dataset from CiteULike was employed. Experimental results show that the proposed approach provides higher quality recommendations than the baseline methods, thus providing a more effective manner to recommend articles in SSN.