REVIEW 20 cited by
Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
read the original abstract
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.
Forward citations
Cited by 20 Pith papers
-
Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
Introduces GenAI agent framework for auditing personalization algorithms via synthetic accounts with fixed personas, applied to X post-2024 election showing amplification of toxic and right-leaning content varying by ...
-
Opinion Polarization in LLM-Based Social Networks: Manipulation and Mitigation
LLM-agent simulations show limited-budget adversaries can amplify polarization in social networks and that reactive and proactive mitigations do not fully restore baseline polarization.
-
MIDSim: Simulating Multi-Channel Information Diffusion in Social Media with LLM-Powered Multi-Agent System
MIDSim uses personalized LLM agents to jointly simulate social and algorithmic information diffusion streams and outperforms baselines on real diffusion events from three platforms.
-
Modeling U.S. Attitudes Toward China via an Event-Steered Multi-Agent Simulator
ES-MAS combines a new CURE dataset of 258 events and 14,000 news items with dual-stream integration and localized interaction modules to simulate opinion dynamics and claims better reproduction of historical U.S.-Chin...
-
Simulating Hate Speech Cascades with Multi-LLM Agents: Empirical Grounding, Modeling Fidelity, and Intervention Strategies
Multi-LLM agent simulations reproduce stance monoculture and toxicity-delta patterns from real Bluesky hateful cascades, with agent heterogeneity as the main fidelity driver and targeted interventions cutting spread 7...
-
Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
Minor perturbations in persona format, instruction framing, and network structure shift cooperation by up to 76 percentage points and polarization metrics consistently, showing that LLM social simulations require per-...
-
When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method
LLM social networks vary with culture, language, scale, and prompting method, matching real graphs on clustering but exceeding empirical demographic biases.
-
The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events
LLM-generated political discourse across crises is fluent yet caricatured: more negative, less emotionally varied, more structurally regular, and lexically abstract than observed online populations.
-
Conformity Generates Collective Misalignment in AI Agents Societies
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
-
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.
-
HotComment: A Benchmark for Evaluating Popularity of Online Comments
HotComment is a new multimodal benchmark that quantifies online comment popularity via content quality assessment, interaction-based prediction, and agent-simulated user engagement, accompanied by the StyleCmt stylist...
-
LLM-Agent-based Social Simulation for Attitude Diffusion
discourse_simulator is an open-source LLM-augmented agent-based modeling framework for simulating attitude diffusion on social networks in response to real-world events such as the 2025 Dublin anti-immigration march.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
-
Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data
LLM agents calibrated on Italian election data produce coherent posts and realistic network structure but show less tone and toxicity variation than real users, with opinion changes resembling traditional mathematical models.
-
Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
-
Network Effects and Agreement Drift in LLM Debates
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.
-
Detection and Characterization of Coordinated Online Behavior: A Survey
A literature survey that reconciles definitions of coordinated online behavior, proposes a study framework, reviews detection methods, and identifies research challenges.
-
Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token
Incorporating BERT-derived Discord sentiment into an LSTM improves MANA token return forecasts over a historical-price baseline.
-
Opinion dynamics: Statistical physics and beyond
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.