A Model of Polarization on Social Media

We develop a model of social media in which users produce different types of content and choose whom to follow. Even when abstracting from algorithmic bias, linking costs shape networks and polarization. In the welfare-maximizing equilibrium, lower linking costs can raise welfare but also increase exposure to extreme content, while very low costs reduce welfare and heighten polarization by discouraging moderate contributors. Policies that incentivize content provision can generate large welfare gains by changing who produces information, whereas link subsidies or attention reallocation mainly affect exposure and have limited welfare impact. These insights help explain why exposure-based interventions on social media platforms often yield ambiguous effects on polarization.