Pro-vaxxer and anti-vaxxer online communities on the social network VKontakte: a comparative analysis of network characteristics

The article examines the VK online communities that actively publish content on the topic of vaccination against SARS-CoV-2 in the period from 01/01/2020 to 03/01/2023. The node in the network is the community, the edge is the fact of having common subscribers. The full network contains 485 nodes, 2488 edges, 5 dyads, 19 isolates, an average of 10 common subscribers, 5 large clusters. The purpose of the article is to compare the network characteristics of communities that declare pro-vaxxer and anti-vaxxer sentiments. The main research method is Social Network Analysis. Anti-vaxxers found a greater degree of self-identification. Anti-vaxxer communities online have an advantage over pro-vaxxer communities in all network criteria: total number, degree of cohesion, various leadership metrics. According to the Degree Centrality metric, which characterizes the valence of the vertex of the graph, almost all large nodes are anti-vaxxer, that is, they have the largest number of common subscribers with other communities. The Betweenness Centrality metric defines the bridge communities that ensure the viability of the network. They connect different clusters in the network, that is, they provide access to adjacent clusters. Among the leaders are 6 anti-vaxxer, 1 pro-vaxxer and 1 neutral communities. The Eigenvector Centrality metric shows which communities have connections to the strongest communities (those with the most connections). According to this criterion, the leaders were 7 anti-vaxxer and 3 pro-vaxxer communities. Anti-vaxxers also form more cohesive clusters than supporters. The network of anti-vaxxer communities is much denser. Pro-vaxxer communities are more fragmented and disconnected: there is no intensive overlap between audiences. The results of the study are also interpreted in the context of the prospect theory of D. Kahneman and A. Tversky, which explains the patterns of behavior of actors when making deci- sions related to risks. In a situation where no one can give guarantees, people choose a risky option that leaves hope of avoiding losses. In a situation of fear both before the new SARS-CoV-2 infection and before the new vaccine against it, the decision not to get vaccinated means a chance not to lose anything. The large weight of anti-vaxxers in the network is explained, on the one hand, by the typical behavior of people in a situation of threat of "losses" in the context of risk theory. The unity of anti-vaxxers is also a consequence of the pattern that a situation where serious losses are possible can be exploited. In contrast to the more relaxed behavior in the network of communities that are in tune with the grand narrative, anti-vaxxer communities strive for activity, consolidation and visibility in the information field. Another factor is that conspiracy theorists are more likely to focus on information that confirms their position and opinion (confirmation bias), which can lead to the emergence of echo chambers.