Combining Recommendation Strategies Can Counter Extreme Social Network Polarization
A modeling study shows that combining structural and opinion similarity in link recommendations can prevent network fragmentation and support moderate ...
A modeling study shows that combining structural and opinion similarity in link recommendations can prevent network fragmentation and support moderate ...
A new two-layer hypergraph model simulates opinion change and workplace switching, with LSTM and XGBoost performing best at estimating its ...
A new formal model, GeSoN, applies bounded rationality and multi-layer geo-social networks to simulate how farmers' opinions spread, polarise and ...
A new agent-based framework derives an empirical criterion that predicts with high accuracy whether public discussions will converge, polarise, or ...
A new model called GA-ODE combines graph attention networks with ordinary differential equation constraints to predict opinion evolution on social ...
A new formal framework called CLUE mathematically models how cooperative exchange drives each learner toward a personal ideal of understanding.
A new agent-based model shows that the human drives for local distinctiveness and global cognitive simplicity are enough to produce ...
A new theoretical paper argues that societies of interacting AI agents can form durable, system-level machine opinions that demand a ...
New research in Nature Communications provides a controlled framework for separating genuine opinion dynamics between AI agents from the shared ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine