How Human is AI? Examining the Impact of Emotional Prompts on Artificial and Human and Responsiveness
This research addresses the impact of emotional cues in human-AI interactions for users and developers, showing carry-over effects into human communication, but it is incremental as it builds on existing work on AI responsiveness.
The study investigated how emotional prompts (praise, anger, blame) affect ChatGPT's performance and subsequent human communication, finding that praise led to the greatest improvement in ChatGPT's answers, while emotional tones influenced its ethical prioritization and carried over to more negative human-human interactions.
This research examines how the emotional tone of human-AI interactions shapes ChatGPT and human behavior. In a between-subject experiment, we asked participants to express a specific emotion while working with ChatGPT (GPT-4.0) on two tasks, including writing a public response and addressing an ethical dilemma. We found that compared to interactions where participants maintained a neutral tone, ChatGPT showed greater improvement in its answers when participants praised ChatGPT for its responses. Expressing anger towards ChatGPT also led to a higher albeit smaller improvement relative to the neutral condition, whereas blaming ChatGPT did not improve its answers. When addressing an ethical dilemma, ChatGPT prioritized corporate interests less when participants expressed anger towards it, while blaming increases its emphasis on protecting the public interest. Additionally, we found that people used more negative, hostile, and disappointing expressions in human-human communication after interactions during which participants blamed rather than praised for their responses. Together, our findings demonstrate that the emotional tone people apply in human-AI interactions not only shape ChatGPT's outputs but also carry over into subsequent human-human communication.