Micro-blog, a new social networking service is being widely used by the public to share ideas, disseminate information, and communicate with each other. Due to the large volume of information involved, it is a challenge to understand the retweet and diffusion process and find different pattern or characteristic on micro-blogs. How do we track the process of micro-blog diffusion and analyze its characteristic from different view? How to track micro-changes (structure pattern) and detect abnormal user behaviors (detail tracking)? Aiming to solve above questions, this paper presents an information diffusion function (IDF) model for analyzing the mechanism of micro-blog retweet and combine visualization to show the dynamic process of information diffusion and track user behaviors. We use the IDF to quantify the process of micro-blog diffusion which is defined by three influential factors: micro-blogs information quantity, micro-blog sentiment and user influence. Then we combine IDF with visualization to analyze the process of micro-blog diffusion and detect abnormal users. Experiments on several real topics have shown that visualization based on our model is useful in detecting interesting micro-blog characteristics and trends.
Graphical Abstract