Unsupervised Feature Selection in Signed Social Networks
Kewei Cheng (arizona state university);Jundong Li (arizona state university);Huan Liu (arizona state university)
The rapid growth of social media services brings large amounts of high-dimensional social media data at an unprecedented rate. Feature selection has shown to be powerful to prepare high-dimensional data for effective machine learning tasks. A majority of existing feature selection algorithms for social media data exclusively focus on positive interactions among linked instances. However, in many real-world social networks, instances may also be negatively interconnected. Recent work shows that the leverage of negative links could improve various learning tasks. To take advantage of negative links, we study a novel problem of unsupervised feature selection in signed social networks and propose a novel framework SignedFS. In particular, we provide a principled way to model positive and negative links for user preference learning. Then we embed the user preference learning into feature selection. Also, we revisit the homophily effect and balance theory in signed social networks and incorporate signed graph regularization into the feature selection framework to capture the first-order proximity and the second-order proximity in signed social networks. Experiments on real-world signed social networks demonstrate the effectiveness of our proposed framework. Further experiments are conducted to understand the impacts of negative links for feature selection.