Expertise Ranking in Human Interaction Networks based on PageRank with Contextual Skill and Activity Measures

We introduce a link intensity-based ranking model for recommending relevant users in human interaction networks. In open, dynamic collaboration environments enabled by Service-oriented Architecture (SOA), it is ever more important to determine the expertise and skills of users in an automated manner. Additionally, a ranking model for humans must consider metrics such as availability, activity level, and expected informedness of users. We present DSARank for estimating the relative importance of users based on the concept of eigenvector centrality in collaboration networks. We test the applicability of our ranking model by using datasets obtained from real human interaction networks including email conversations and cellular phone communications. The results show that DSARank is better suited for recommending users in collaboration networks than traditional degree-based methods. Furthermore, we show applications of DSARank in emerging Service-oriented environments. We present ranking and recommendation in a system where humans can provide services based on their expertise.