Predicting user influence in microblogs

摘要

User influence can be described as power - the ability of a person to influence the thoughts or actions of others. In this paper, we investigate the attributes of 244,175 users and the content of their messages, and they are from Sina Weibo which is one of the most notable micro-blogging services. Our first insight is to quantify the influence of individuals within a period of time by using a novel approach. Our second insight is to predict the influence of every user with higher precision. Our third insight is to find the influence of most users changing over time but changing slightly as a whole. In this paper, we include findings from our study.