Classifying social groups and change point detection for prioritizing social data

Internet technologies and web based social networking have seen wide adopted in the recent years and the user is exposed to lots of data from his friends and acquaintances. The data presented to the user needs to be filtered based on his current state and prioritized. In this paper we propose a method for identifying change points related to busy and free periods based on mobile phone call detail records. This could be used to measure the level of willingness level of users for social interaction. This work is useful for preparing elastic list of updates from close friends and also in optimizing the caching of recent updates at mobile handsets. For validation of our results, we used actual call logs of 100 users collected at MIT. The experimental results show that our method is able to detect the bands achieves results with high accuracy.