Temporal Pattern of Retweet(s) Help to Maximize Information Diffusion in Twitter

Abstract

Twitter is currently a popular microblogging platform for spread of information by users in the form of tweet messages. Such tweets are shared with followers of the seed user who may reshare it with their own set of followers. Long chain of such retweets form cascades. For effective diffusion of information through such Twitter cascades, we identify two different objectives based on using temporal sequence of retweets. Firstly, we aim to infer the structure of influence trees of Twitter cascades, denoting the who-influenced-whom relationship among retweeting users in the cascade, that can play a significant role in identifying critical paths in the network for information dissemination. The constructed trees closely resemble ground truth influence trees of empirical cascades with high retweet count. Secondly, we propose a fast and efficient algorithm for detection of influential users by identifying anchor nodes from temporal retweet sequence. Identification of such a diverse set of influential users enable a faster diffusion of tweets to a large and diverse population, when targeted as seeds thereby maximizing the influence spread, facilitating several applications including viral marketing, disease control and news dissemination.