Genetic Algorithm Based Model for Identifying Communities in Social Network (Instagram)

Today, the analysis of information in social networks has attracted the attention of many researchers. Commercial, political and socio-cultural motives have also increased the importance of this. Recognizing communities in complex networks or social networks is one of the most important problems in the scientific field. Given the proliferation of social networking databases, scalable algorithms are needed to analyze these networks. Finding communities in a social network is one of the ways in which a social network can be explored. Due to the fact that search methods have a high sampling rate and are not suitable in terms of execution time and sometimes accuracy, a new method was proposed in which the network is divided into several specific parts and each part is a factor. Explores randomly in no particular order. The results show that the proposed method is much more suitable in terms of the sum of all three factors than other classical methods. In this study, three methods of random walking, snowball and first level search and the proposed EGACD method for identifying communities on the social network (Instagram) have been compared. The results for the social network (Instagram) with ۸۰۸۱ members were analyzed by MATLAB programming. The study is based on three factors: execution time, sampling rate and accuracy. The results show that the proposed EGACD method will improve the results in terms of factors such as sampling rate, accuracy and execution time.

Keywords:

social network , genetic algorithm , community identification , (Instagram)