A new machine learning framework has been developed to detect and analyze coordinated foreign influence operations in online news comments. This framework, applied to over 112 million South Korean news comments from 4 million users over 20 years, identified nearly 24,000 accounts exhibiting manipulative behavior. The analysis revealed that these accounts primarily use morally condemning rhetoric, which garners higher user engagement, often targeting domestic political figures to potentially amplify polarization. The framework aims to support transparent platform governance and inform moderation strategies against harmful narrative-target combinations. AI
IMPACT This research could lead to more effective AI-driven moderation tools for online platforms to combat disinformation and polarization.
RANK_REASON The cluster contains an academic paper detailing a new machine learning framework for analyzing online troll behavior. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
