arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12763cs.HCcs.AI
收藏

不是人类,更有趣:机器身份如何塑造在线AI单口喜剧的幽默感知

"Not Human, Funnier": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy

The University of Hong Kong Hong Kong, SAR China;Carnegie Mellon University\ -Computer Interaction Institute Pittsburgh United States;East China Normal University Shanghai China;Northeastern University\ of Art, Media;City University of Hong Kong\ for Narrative Spaces Hong Kong, SAR China;The University of Hong Kong;Carnegie Mellon University\ -Computer Interaction Institute;East China Normal University;City University of Hong Kong\ for Narrative Spaces

Xuehan Huang, Canwen Wang, Yifei Hao, Daijin Yang, Ray LC

AI总结:

本研究探讨了AI身份如何影响幽默感知,通过设计基于机器身份的代理,发现其在单口喜剧表演中比基线GPT代理更有趣,提出人机集成系统应明确利用AI的独特身份。

摘要:

聊天机器人正在被越来越多地应用于以前由人类演员主导的领域。其中喜剧就是一个例子,无论是普通公众使用ChatGPT还是基于研究的LLM系统,都尝试涉足幽默创作。通过与专业喜剧演员的形成性访谈和对人类单口喜剧视频的分析,我们发现人类表演者常常利用其种族、性别、社区和人口统计数据身份来促进笑话创作。这表明,AI自身的身份是否能够为人类观众赋能AI幽默生成。我们设计了一个基于机器身份的代理,利用其作为AI的身份在在线表演格式中讲笑话。针对人类观众(N=32)的研究显示,基于机器身份的代理被认为比基线GPT代理更有趣。这项工作表明,应设计出能够明确利用AI作为自身独特身份(而非人类)的人机集成系统。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑