"Not Human, Funnier": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy
This work addresses the challenge of making AI-generated humor more engaging for online audiences, though it is incremental as it builds on existing AI comedy efforts.
The study tackled the problem of AI humor generation by exploring whether explicitly using AI's machine identity in jokes makes them funnier for human audiences, finding that a machine-identity-based agent was perceived as funnier than a baseline GPT agent in tests with 32 participants.
Chatbots are increasingly applied to domains previously reserved for human actors. One such domain is comedy, whereby both the general public working with ChatGPT and research-based LLM-systems have tried their hands on making humor. In formative interviews with professional comedians and video analyses of stand-up comedy in humans, we found that human performers often use their ethnic, gender, community, and demographic-based identity to enable joke-making. This suggests whether the identity of AI itself can empower AI humor generation for human audiences. We designed a machine-identity-based agent that uses its own status as AI to tell jokes in online performance format. Studies with human audiences (N=32) showed that machine-identity-based agents were seen as funnier than baseline-GPT agent. This work suggests the design of human-AI integrated systems that explicitly utilize AI as its own unique identity apart from humans.