Applying Answer Set Programming for Knowledge-Based Link Prediction on Social Interaction Networks

Abstract

Link prediction targets the prediction of possible future links in a social network, i. e., we aim to predict the next most likely links of the network given the current state. However, predicting the future solely based on (scarce) historic data is often challenging. In this paper, we investigate, if we can make use of additional (domain) knowledge to tackle this problem. For this purpose, we apply answer set programming (ASP) for formalizing the domain knowledge for social network (and graph) analysis. In particular, we investigate link prediction via ASP based on node proximity and its enhancement with background knowledge, in order to test intuitions that common features, e. g., a common educational background of students, imply common interests. In addition, then the applied ASP formalism enables explanation-aware prediction approaches.