Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation

• URL: http://arxiv.org/abs/2508.03385v1
• Date: Tue, 05 Aug 2025 12:31:52 GMT
• Title: Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation
• Authors: Maik Larooij, Petter Törnberg,
• Abstract summary: generative social simulation embeds Large Language Models within Agent-Based Models to create socially rich synthetic platforms.<n>We create a minimal platform where agents can post, repost, and follow others.<n>We find that the resulting following-networks reproduce three well-documented dysfunctions: (1) partisan echo chambers; (2) concentrated influence among a small elite; and (3) the amplification of polarized voices.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Social media platforms have been widely linked to societal harms, including rising polarization and the erosion of constructive debate. Can these problems be mitigated through prosocial interventions? We address this question using a novel method - generative social simulation - that embeds Large Language Models within Agent-Based Models to create socially rich synthetic platforms. We create a minimal platform where agents can post, repost, and follow others. We find that the resulting following-networks reproduce three well-documented dysfunctions: (1) partisan echo chambers; (2) concentrated influence among a small elite; and (3) the amplification of polarized voices - creating a 'social media prism' that distorts political discourse. We test six proposed interventions, from chronological feeds to bridging algorithms, finding only modest improvements - and in some cases, worsened outcomes. These results suggest that core dysfunctions may be rooted in the feedback between reactive engagement and network growth, raising the possibility that meaningful reform will require rethinking the foundational dynamics of platform architecture.

Related papers

• Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation [10.262762637015733]
  We introduce a social underlinerecommendation model with rounderlinebust gunderlineraph denoisinunderlineg-augmentation fusion and multi-sunderlineemantic Modeling(Burger)<n>Considering the different semantic information in the user-item interaction network and the social network, a bi-semantic coordination loss is proposed to model the mutual influence of semantic information.
  arXiv  Detail & Related papers  (2025-05-10T11:51:22Z)
• Emergence of human-like polarization among large language model agents [79.96817421756668]
  We simulate a networked system involving thousands of large language model agents, discovering their social interactions, result in human-like polarization.<n>Similarities between humans and LLM agents raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.
  arXiv  Detail & Related papers  (2025-01-09T11:45:05Z)
• TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System [90.09422823129961]
  We propose TrendSim, an LLM-based multi-agent system to simulate trending topics in social media under poisoning attacks.<n>Specifically, we create a simulation environment for trending topics that incorporates a time-aware interaction mechanism, centralized message dissemination, and an interactive system.<n>We develop LLM-based human-like agents to simulate users in social media, and propose prototype-based attackers to replicate poisoning attacks.
  arXiv  Detail & Related papers  (2024-12-14T12:04:49Z)
• Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks [12.812531689189065]
  Impact of social media on critical issues such as echo chambers needs to be addressed.<n>Traditional research often oversimplifies emotional tendencies and opinion evolution into numbers and formulas.<n>We propose an LLM-based simulation for the social opinion network to evaluate and counter polarization phenomena.
  arXiv  Detail & Related papers  (2024-09-28T12:49:02Z)
• Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting [74.68371461260946]
  SocialSense is a framework that induces a belief-centered graph on top of an existent social network, along with graph-based propagation to capture social dynamics. Our method surpasses existing state-of-the-art in experimental evaluations for both zero-shot and supervised settings.
  arXiv  Detail & Related papers  (2023-10-20T06:17:02Z)
• Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms [8.602553195689513]
  Social media is often criticized for amplifying toxic discourse and discouraging constructive conversations. This paper asks whether simulating social media can help researchers study how different news feed algorithms shape the quality of online conversations.
  arXiv  Detail & Related papers  (2023-10-05T18:26:06Z)
• Crowding out the truth? A simple model of misinformation, polarization and meaningful social interactions [0.0]
  We evaluate the effect of key parameters of ranking algorithms, namely popularity and personalization parameters, on measures of platform engagement, misinformation and polarization. The results show that an increase in the weight assigned to online social interactions and to personalized content may increase engagement on the social media platform, while at the same time increasing misinformation and/or polarization.
  arXiv  Detail & Related papers  (2022-10-05T13:26:08Z)
• Hater-O-Genius Aggression Classification using Capsule Networks [6.318682674371969]
  We propose an end-to-end ensemble-based architecture to automatically identify and classify aggressive tweets. Tweets are classified into three categories - Covertly Aggressive, Overtly Aggressive, and Non-Aggressive. Our best model is an ensemble of Capsule Networks and results in a 65.2% F1 score on the Facebook test set, which results in a performance gain of 0.95% over the TRAC-2018 winners.
  arXiv  Detail & Related papers  (2021-05-24T11:53:58Z)
• PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception [50.551003004553806]
  We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions. Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
  arXiv  Detail & Related papers  (2021-03-02T18:44:57Z)
• CASS: Towards Building a Social-Support Chatbot for Online Health Community [67.45813419121603]
  The CASS architecture is based on advanced neural network algorithms. It can handle new inputs from users and generate a variety of responses to them. With a follow-up field experiment, CASS is proven useful in supporting individual members who seek emotional support.
  arXiv  Detail & Related papers  (2021-01-04T05:52:03Z)
• Echo Chambers on Social Media: A comparative analysis [64.2256216637683]
  We introduce an operational definition of echo chambers and perform a massive comparative analysis on 1B pieces of contents produced by 1M users on four social media platforms. We infer the leaning of users about controversial topics and reconstruct their interaction networks by analyzing different features. We find support for the hypothesis that platforms implementing news feed algorithms like Facebook may elicit the emergence of echo-chambers.
  arXiv  Detail & Related papers  (2020-04-20T20:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.