Link value and event-result prediction for sequence behavior in social networks

With the development of on-line social networks, increasing numbers of functions are provided to social members. These social members can join different kinds of activities that are presented as events. Some events may include many user-interaction behaviors, and the results of such events are determined by the kinds of behaviors. If each behavior is presented as a link, the sign value of the link may represent the kind of behavior. Link prediction is the focus for predicting the value of these links. Many studies have been performed on solving link-prediction problems. However, most of them were performed in static network environments, and each link was predicted independent of the others. Those researchers treated user behavior for such events as "normal behavior," which were treated individually and discretely. Therefore, the correlation of those links that were created during the event was not considered. In this paper, we model these event behaviors as "sequence behavior", and proposed sequence-behavior-based link-prediction and event-prediction methods. In our method, we can accumulate the sequence information of behaviors, and can predict the next one or several link values in the sequence. When we finish predicting the entire sequence, the events result may be inferred. The experiment results show that our method outperforms the static and individual link-prediction methods. The events result may be better predicted at the same time.