Information flow modeling based on diffusion rate for prediction and ranking

less than 1 minute read

by Song et al. (song2007)

Song et al. investigate the information flow in a user network. They try to (i) predict where information flows and (ii) who will most quickly receive that information given a certain sender. The authors introduce a DiffusionRank algorithm which ranks users based on the time information needs to flow to them.

As Goya et al. (goya2010) Song et al (song2007) note that information flow modeling is related to word-of-mouth communication and therefore heavily influence by the social influence of the actors.

The authors suggest an information flow model which is based on a Continuous-Time Markov Chain (CTMC). In the conclusions Song et al. (song2007) argue that a social network user's influence is somehow related to the importance of Web pages as suggested by the HITS or PageRank measures.