Kemo Adrian, Paula Chocrón, Roberto Confalonieri, Xavier Ferrer, Jesús Giráldez-Cru

Link Prediction in Evolutionary Graphs: The Case Study of the CCIA Network

CCIA 2016

Studying the prediction of new links in evolutionary networks is a captivating question that has received the interest of different disciplines. Link prediction allows to extract missing information and evaluate network dynamics. Some algorithms that tackle this problem with good performance are based on the sociability index, a measure of node interactions along time. In this paper, we present a case study of this predictor in the evolutionary graph representing the CCIA co-authorship network from 2005 to 2015. We present a generalized version of this sociability index, that takes into account when such interactions occur. We show that some variants of this new index outperform existing predictors.