Intuitive prompting helps AI simulate social media reactions better
Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content
Artificial IntelligenceComputation and LanguageHuman-Computer InteractionMultiagent SystemsSocial and Information Networks
Summary
It can be hard for AI models to act like real social media users with believable profiles. The authors studied how well AI could predict people’s reactions to posts when given different types of profile information. They found that telling AI to respond quickly based on intuition worked better than asking it to analyze carefully. This method made AI reactions more like the real individuals they were trying to mimic, even on topics the AI hadn’t seen before.
What this means in practice
- •For platform policy teams: Validate artificial user behavior in social media testing to ensure agents match given profiles realistically.
- •For social media marketers: Create AI-driven simulated users that provide believable reactions across various content to test marketing impact.$Commercial implications: Enables development of AI tools that mimic individual social media users, enhancing marketing campaign simulations.
Authors
Ljubisa Bojic, Tijana Stanic, Joerg Matthes, Agariadne Dwinggo Samala, Bojana Dinic, Jue Wang
Abstract
Platform policies are increasingly tested on artificial users, making agent fidelity important. Yet convincing fake profiles could also manipulate perceived public opinion before elections. Validation has concentrated on agreement with human behaviour and has paid little attention to whether an agent behaves in line with the profile it was given. The present study profiled eight Serbian participants through a questionnaire, a deep interview, and a written self-presentation, recorded their reactions to sixty-eight social media posts, and asked four language models to predict those reactions under five prompt conditions varying profile content and instruction style. Attitudinal content improved prediction over demographic backstories by a wide margin. Agents matched their stated profiles more closely than participants matched their own survey answers, and consistency proved unrelated to fidelity once profile information was present. Instructing models to respond intuitively and immediately rather than analytically gave the highest fidelity of any condition and cut the compression of individual differences from seven times the human level to three. The advantage held on posts about topics the questionnaire never raised, where that condition reached the highest fidelity of any setup and beat a crowd baseline by a wide margin, which suggests that agents prompted this way could serve as general-purpose simulated users rather than specialists on the topics they were profiled for. Results may bear implications for the development of language models, because intuition-based setups appear better suited to some tasks than reasoning-based ones.