The paper “Leveraging content producer networks and user perception to detect online discursive communities” has been accepted for publication in Scientific Reports.
In this work, we develop a method to identify discussion communities on social media by first clustering influential “leader” users and then using these clusters to classify the broader user base, showing that this better captures underlying political divisions than standard approaches.
This provides a useful basis for future studies on how social dynamics shape epidemic outcomes through ideologically grounded interacting subpopulations.