Inference of social media opinion trends in 2022 Italian elections

Social media platforms play a significant role in political discourse, often serving as tools for political actors to disseminate partisan narratives, frequently encapsulated in concise slogans presented as hashtags. In this paper, we present a novel systematic framework leveraging network science tools and clustering algorithms to discern the political orientations of posts through their associated hashtags, that can be used in the context of opinion dynamics. Our results show that by applying this framework within the context of the 2022 Italian Elections, we successfully quantify the online activity of political coalitions and their supporters pre and post-election. By analyzing labeled posts derived from this framework we find a surge in user activity leading up to the election, followed by a pronounced decline afterward. Moreover, we note a remarkable shift in engagement toward the winning coalition post-election. Interestingly, at the coalition level, our findings reveal an inverse correlation between posting activity and the level of engagement received on social media platforms. Finally, a rank-size analysis of publication patterns among supporters during the pre-election period highlighted comparable trends in content generation across coalitions.