Opinion-based Homogeneity on YouTube: Combining Sentiment and Social Network Analysis

Abstract

When addressing public concerns such as the existence of politically like-minded communication spaces in social media, analyses of complex political discourses are met with increasing methodological challenges to process communication data properly. To address the extent of political like-mindedness in online communication, we argue that it is necessary to focus not only on ideological homogeneity in online environments, but also on the extent to which specific political questions are discussed in a uniform manner. This study proposes an innovative combination of computational methods, including natural language processing and social network analysis, that serves as a model for future research examining the evolution of opinion climates in online networks. Data were gathered on YouTube, enabling the assessment of users’ expressed opinions on three political issues (i.e., adoption rights for same-sex couples, headscarf rights, and climate change). Challenging widely held assumptions on discursive homogeneity online, the results provide evidence for a moderate level of connections between dissimilar YouTube comments but few connections between agreeing comments. The findings are discussed in light of current computational communication research and the vigorous debate on the prevalence of like-mindedness in online networks.

Caught in a networked collusion? Homogeneity in conspiracy-related discussion networks on YouTube

“…Indeed, this formation of homogeneous subgroups in online communication has been a longstanding concern since the emergence of the Internet and even more salient since the rise of social media platforms [11], [12]. Empirical evidence, however, has repeatedly shown that while social media users are more likely to be connected with like-minded others, they-often incidentally-interact and become exposed to content or opinionated messages that challenge their personal viewpoint or ideology [13], [46]- [50].…”

“…Specifically, this concept refers to the degree to which messages (e.g., user-generated comments) that are semantically similar are connected in the network. Opinion-based homogeneity [13] can be measured by the global E-I index [54], which is defined as follows:…”

“…

Addressing the prevalence of homogeneity in online networks, previous research indicated that in the case of networks discussing three politically relevant topics on YouTube, follow-up comments were more likely to express opposing views than similar opinions [13].Discussions on conspiracy theories, however, might be structured differently: The spiral of silence theory [14] predicts that people are more inclined to express themselves in situations in which they feel part of the majority. Drawing on this, one could assume that supporters of conspiracy theories-as social minorities-might only voice their viewpoints in contexts in which they encounter agreement.

…”

“…Addressing the prevalence of homogeneity in online networks, previous research indicated that in the case of networks discussing three politically relevant topics on YouTube, follow-up comments were more likely to express opposing views than similar opinions [13].…”

The influence of community structure on opinion expression: an agent-based model

“…Political or opinion-based homogeneous discussion areas have already been examined on Facebook (Bakshy et al 2015 ), YouTube (Röchert et al 2020 ) and Twitter (Barberá et al 2015 ), but the aspect of the individual communities within the network has largely been ignored. Williams et al ( 2015 ) analysed the Twitter communication network on climate change using a network analysis and found that there is a strong homogeneity in the interactions between like-minded communities of climate change activists and climate sceptics.…”