Analysing the Competency of Various Decision Trees towards Community Formation in Multiple Social Networks

Abstract

Multiple Online Social Networks and its applications have emerged rapidly at a large scale made dependence of global population on it for various reasons. The individuals data in each social network is just partial. Mapping these individuals across various online social networks is having more importance in forming communities and identifying the most influential node. The difficulties of fragmentary data which is the biggest challenge in the present social network era can be solved by forming groups and comparing their information which can be useful in several applications like influential node detection, spammer identification etc. The occurrence of different characterization of users leads in identifying the influential community by classifying them from other communities. Decision tree technique is used in splitting into different communities from multiple social network. Various number of trees are generated by changing class labels. Greater the performance metrical values (accuracy, precision, recall, f1-score) of the tree is considered for the effective formation of communities. Experimental results of the proposed method achieves 0.54, 0.58, 0.54, 0.54 in accuracy, precision, recall, and f1-measure, respectively.