Simulating Social Media Using Large Language Models

Social media is often criticized for amplifying toxic discourse and discouraging constructive conversations. But designing social media platforms to promote better conversations is inherently challenging. This lecture asks whether simulating social media through a combination of Large Language Models (LLM) and Agent-Based Modeling can help researchers study how the algorithms and affordances of social media shape the quality of online conversations. The lecture argues that LLMs hold considerable potential to improve simulation research on social media and many other complex social settings.