Title: The homophily principle in social network analysis: A survey

Abstract

In recent years, Social media has become a ubiquitous and integral part of social discourse. Homophily is a fundamental topic in network science and can provide insights into the flow of information and behaviours within society. Homophily mainly refers to the tendency of similar-minded people to interact with one another in social groups than with dissimilar-minded people. The study of homophily has been very useful in analyzing the formations of online communities and has been vastly studied in different types of social media data, ranging from textual data (Twitter tweets) to follower lists of online social accounts. However, no detailed survey has been conducted to date based on the works of social media networks related to the homophily principle. Therefore, the main aim of this article is to focus on providing a thorough review of the related works conducted on social media networks based on the homophily principle. We review and survey the effects of homophily in social networks and summarize the state-of-art methods that have been proposed in recent years to identify and measure those effects in multiple types of social networks. The homophily principle was also used to study the exchanging views about global warming on Twitter. The online debate on climate change was studied, and the degree of homophily among the individuals was measured on the number of times the edges were connecting users on homogeneous/ heterogeneous views. The high frequency of edges between the homogeneous users, and similarly, the low frequency of edges between the heterogeneous users were considered as the measure of homophily. The users' attitudes towards global warming were classified based on their message content. The social networks were categorized by opinion-based homophily and the users were manually labelled as "skeptic" and "activist" groups based on their message content. Results have shown that users generally communicate only with other similar-minded users, in communities that are influenced by a common view. Moreover, the messages of like-minded users have shown to be a positive sentiment in most cases, whereas, messages from skeptics held a more negative sentiment.