Link Prediction in Microblog Network Using Supervised Learning with Multiple Features

Abstract

Link prediction (LP) is a fundamental network analysis task. It aims to analyze the existing links and predict the missing or potential relations between users in a social network. It can help users in finding new friends, enhance their loyalties to the web sites and build a healthy social environment. In previous researches, much attention was focused on structure information or node attributes, in order to analyze the global or local properties. Considering the nature of Microblog social network, we proposed a link prediction system combining multiple features from different perspectives, and learn a classifier from these feature subsets to predict the potential links. We train classifiers using SVM, Nai ve Bayes, and Random Forest and Logistic Regression algorithms and evaluate them using the microblog network dataset. The results show that our features perform better than the traditional features, and the combination of multiple features can achieve highest accuracy.