A New Method for Prediction of Future Links in Social Networks Using Data Preprocessing by Mining Tools

Abstract

Social networks are primarily represented and analyzed in the form of graphs with a large number of vertices and edges in the form of an adjacency matrix. Edges represent relationships between individuals and act as links between vertices. The structural properties of each network are determined by the features of the edges and vertices within it. In this research conducted on various types of social networks data from the Stanford University database, preprocessing method using a competitive colonial algorithm was employed for feature selection operations, selecting features with the highest competence (lowest cost). To evaluate the impact of feature selection on the final output, experiments were conducted with and without feature selection operations using different algorithms commonly used in this field. Valid indices such as accuracy, detection, sensitivity, and major were independently measured on the output results with an average of 10 program executions. Comparing the results between scenarios with and without feature selection showed a significant impact on all final result indicators. Many features in the datasets were either unused or contained minimal information. Not removing these features not only increased computational burden but also affected the accuracy of the output results due to time-consuming executions.