Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
This research addresses the challenge of reducing toxic discourse on social media for platform designers and researchers, though it is incremental in applying existing simulation methods to a new context.
The paper tackled the problem of designing social media platforms to improve online conversations by simulating social media using Large Language Models and Agent-Based Modeling to evaluate different news feed algorithms, finding that a novel 'bridging' algorithm promoted more constructive and non-toxic conversations across political divides compared to traditional algorithms.
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 paper asks whether simulating social media through a combination of Large Language Models (LLM) and Agent-Based Modeling can help researchers study how different news feed algorithms shape the quality of online conversations. We create realistic personas using data from the American National Election Study to populate simulated social media platforms. Next, we prompt the agents to read and share news articles - and like or comment upon each other's messages - within three platforms that use different news feed algorithms. In the first platform, users see the most liked and commented posts from users whom they follow. In the second, they see posts from all users - even those outside their own network. The third platform employs a novel "bridging" algorithm that highlights posts that are liked by people with opposing political views. We find this bridging algorithm promotes more constructive, non-toxic, conversation across political divides than the other two models. Though further research is needed to evaluate these findings, we argue that LLMs hold considerable potential to improve simulation research on social media and many other complex social settings.