Shahrekord University


Estimating similarity is expressed in many domains and sciences. For instance, data mining, web mining, clustering, search engines, ontology mapping and social networks require the definition and deployment of similarity. User similarity in social networks is one of the main problems and has many applications in this area. In this paper, a new method is introduced for combining structural and non-structural similarity between users in social networks. In the experimental section, structural similarity algorithms are combined with non-structural similarity algorithms through the proposed method. All experiments are implemented on some part of the Twitter dataset. Experimental results show that the precisions of all algorithms are increased with the proposed method.