# Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation

arXiv: https://arxiv.org/abs/2502.12073 · HTML: https://mlsanity.com/paper/2502.12073/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation](https://mlsanity.com/paper/2402.16333/) (2024)
- [Y Social: an LLM-powered Social Media Digital Twin](https://mlsanity.com/paper/2408.00818/) (2024)
- [Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation](https://mlsanity.com/paper/2501.04167/) (2025)
- [Artificial Intelligence for Health Message Generation: Theory, Method, and an Empirical Study Using Prompt Engineering](https://mlsanity.com/paper/2212.07507/) (2022)
- [Social Media Study of Public Opinions on Potential COVID-19 Vaccines: Informing Dissent, Disparities, and Dissemination](https://mlsanity.com/paper/2012.02165/) (2020)
- [PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction](https://mlsanity.com/paper/2402.18950/) (2024)
- [Classifying Human-Generated and AI-Generated Election Claims in Social Media](https://mlsanity.com/paper/2404.16116/) (2024)

## Built on by (most cited first, 9 of 9)

- [MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations](https://mlsanity.com/paper/2504.07830/) (2025)
- [textttBluePrint: A Social Media User Dataset for LLM Persona Evaluation and Training](https://mlsanity.com/paper/2510.02343/) (2025)
- [HotComment: A Benchmark for Evaluating Popularity of Online Comments](https://mlsanity.com/paper/2604.25614/) (2026)
- [PHORECAST: Enabling AI Understanding of Public Health Outreach Across Populations](https://mlsanity.com/paper/2510.02535/) (2025)
- [Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models](https://mlsanity.com/paper/2510.18454/) (2025)
- [Predicting Social Media User Actions: A Hybrid Approach for Common and Rare Behavior Prediction on Bluesky](https://mlsanity.com/paper/2511.17241/) (2025)
- [Assessing Capabilities of Large Language Models in Social Media Analytics: A Multi-task Quest](https://mlsanity.com/paper/2604.18955/) (2026)
- [Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions](https://mlsanity.com/paper/2606.06443/) (2026)
- [PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation](https://mlsanity.com/paper/2610.14570/) (2026)

## Abstract (arXiv)

Social media enables dynamic user engagement with trending topics, and recent research has explored the potential of large language models (LLMs) for response generation. While some studies investigate LLMs as agents for simulating user behavior on social media, their focus remains on practical viability and scalability rather than a deeper understanding of how well LLM aligns with human behavior. This paper analyzes LLMs' ability to simulate social media engagement through action guided response generation, where a model first predicts a user's most likely engagement action-retweet, quote, or rewrite-towards a trending post before generating a personalized response conditioned on the predicted action. We benchmark GPT-4o-mini, O1-mini, and DeepSeek-R1 in social media engagement simulation regarding a major societal event discussed on X. Our findings reveal that zero-shot LLMs underperform BERT in action prediction, while few-shot prompting initially degrades the prediction accuracy of LLMs with limited examples. However, in response generation, few-shot LLMs achieve stronger semantic alignment with ground truth posts.