Gravity Well Echo Chamber Modeling With An LLM-Based Confirmation Bias Model

Social media echo chambers play a central role in the spread of misinformation, yet existing models often overlook the influence of individual confirmation bias. An existing model of echo chambers is the "gravity well" model, which creates an analog between echo chambers and spatial gravity wells. We extend this established model by introducing a dynamic confirmation bias variable that adjusts the strength of pull based on a user's susceptibility to belief-reinforcing content. This variable is calculated for each user through comparisons between their posting history and their responses to posts of a wide range of viewpoints.