Abstract:

Proximity measurement between objects is a key problem of the clustering method. The email feature vector was introduced, and the email feature matrix was constructed. The information of email features was fitted by the model of the transformed extremal value distribution function. Based on this, EVS(extreme value distribution similarity) was proposed for email community clustering. The effectiveness of the new measurement was verified by the micromacro clustering algorithm. Experiments show that compared to cosine-based similarity and Pearson correlation coefficient, the algorithm using the new proposed similarity measurement can identify higher quality communities.

Key words: social network; email community partition; extreme value distribution; EVS similarity