Contextualizing Online Conversational Networks

Abstract

Online social connections occur within a specific conversational context. Prior work in network analysis of social media data attempts to contextualize data through filtering. We propose a method of contextualizing online conversational connections automatically and illustrate this method with Twitter data. Specifically, we detail a graph neural network model capable of representing tweets in a vector space based on their text, hashtags, URLs, and neighboring tweets. Once tweets are represented, clusters of tweets uncover conversational contexts. We apply our method to a dataset with 4.5 million tweets discussing the 2020 US election. We find that even filtered data contains many different conversational contexts, with users engaging in multiple conversations. While users engage in multiple conversations, the overlap between any two pairs of conversations tends to be only 30-40%, giving very different networks for different conversations. Even accounting for this variation, we show that the relative social status of users varies considerably across contexts, with tau=0.472 on average. Our findings imply that standard network analysis on social media data can be unreliable in the face of multiple conversational contexts.