Examining the correlation between metrics in the Instagram social network to identify fake pages and improve marketing

Abstract

Considering the increasing role of social networks in daily life and their role in developing businesses, paying close attention to each of them and their different dimensions is particularly important. As one of the social networks, Instagram has a global scope and an essential role in the field of interpersonal communication in various personal and professional dimensions. One of the significant problems in this platform is the existence of fake accounts with incorrect statistics. In this research, by analyzing the pages of Instagram users, the association between the metrics used to measure the performance of these pages has been investigated. For this purpose, the data of 1860 public pages on Instagram were collected as metrics of the number of followers, comments, likes, posts, followers, and the post's topic. The hypotheses test results show a statistically significant correlation between the number of posts and likes. However, there is no statistically significant association between the number of likes and comments, the number of followers and comments, and the number of followers and likes. The analysis of 100 verified Instagram pages shows that the proposed method can distinguish real from fake pages with 94% accuracy and should be considered in business marketing ads on Instagram. The comparison of results with other classification methods revealed the efficiency of the proposed method.