Are LLM-Powered Social Media Bots Realistic?
By: Lynnette Hui Xian Ng, Kathleen M. Carley
Potential Business Impact:
Makes fake social media accounts seem real.
As Large Language Models (LLMs) become more sophisticated, there is a possibility to harness LLMs to power social media bots. This work investigates the realism of generating LLM-Powered social media bot networks. Through a combination of manual effort, network science and LLMs, we create synthetic bot agent personas, their tweets and their interactions, thereby simulating social media networks. We compare the generated networks against empirical bot/human data, observing that both network and linguistic properties of LLM-Powered Bots differ from Wild Bots/Humans. This has implications towards the detection and effectiveness of LLM-Powered Bots.
Similar Papers
Are LLM-Powered Social Media Bots Realistic?
Social and Information Networks
Shows AI bots differ from real users online
Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data
Social and Information Networks
Computers can now pretend to be people online.
Social Simulations with Large Language Model Risk Utopian Illusion
Computation and Language
Computers show fake, too-nice people in chats.