User Follow Prediction of Microblog Based on the Activeness and Interest Similarity

Abstract

Many microblog fans have formed the basis of microblog information dissemination and diffusion, so accurate prediction and attracting more potential customers to follow microblogger becomes very necessary. By employing interpersonal relationship network of microblog fans, this study integrates microblogger popularity and user activeness into interest similarity in order to explain user follow predictor and propose user follow prediction models. Support vector machine (SVM) is used to train this model. Open data from Tencent microblog in KDD Cup 2012 prove that the proposed prediction model has higher prediction accuracy and stability.
Key words: Microblog; User follow; Microblogger popularity; User activeness; Interest similarity; Prediction model