Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes

2026-06-12 · Source: cs.AI updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Expert, quick

Summary

A study by Anna-Maria Velentza and Anne-Gwenn Bosser, accepted at the 35th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2026), investigated how humor style, joke content, and language influence perceptions of AI-generated jokes delivered by robots. Conducted in a university classroom, the exploratory research used a mixed factorial design where participants evaluated bilingual robot-delivered humor. Results indicate that humor type significantly impacts perceived funniness, with Aggressive and Affiliative styles receiving higher ratings. Conversely, joke content primarily determines appropriateness, showing a preference for person-related jokes over political ones. Furthermore, language preference for robot-delivered humor was influenced by both the joke's content and participants' self-reported language fluency and humor habits.

Key takeaway

For AI Scientists and Robotics Engineers developing conversational agents with humor capabilities, you should prioritize humor style over content for eliciting laughter. Focus on generating Affiliative or Aggressive humor types, as these were rated funnier. Crucially, avoid political joke content to maintain appropriateness and user acceptance. Consider user language fluency and humor practices when designing bilingual humor systems to optimize engagement and positive reception.

Key insights

Humor style dictates funniness, while joke topic determines acceptability for robot-delivered AI jokes.

Principles

• Aggressive and Affiliative humor styles are perceived as funnier.
• Person-related jokes are more appropriate than political ones.
• Language preference depends on joke content and user fluency.

Method

Employed a mixed factorial design where participants evaluated AI-generated jokes delivered by a robot in a university classroom, varying humor type and joke content.

In practice

• Prioritize Affiliative or Aggressive humor for robot joke generation.
• Avoid political topics for robot-delivered humor.

Topics

• Human-Robot Interaction
• Computational Humor
• AI Joke Generation
• Humor Perception
• Robot-Delivered Humor
• Bilingual Interaction

Best for: AI Scientist, Robotics Engineer, Research Scientist

Related on AIssential

• Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes — Aggressive and Affiliative humor styles enhance robot-delivered joke funniness, while person-related topics improve appropriateness.
• Emma the joke-telling robot cracks up the care home: Paula Hornickel’s best photograph — Social robots offer companionship and engagement in care settings, but cannot replace human connection.
• An Eight-Week Analysis of Accept-Language Headers Across Major AI Bots — The article details an eight-week analysis of Accept-Language headers used by major AI bots.
• Re-defining Humor Data Objects for AI Humor Research — AI humor research improves by defining humor as a social interaction with context and explanations, not just a binary state.
• Understanding Sarcasm in Generative AI Models: How ChatGPT Interprets Human Intent — Sarcasm detection in AI requires understanding non-literal meaning through contextual learning, moving beyond simple keyword analysis.
• Donald Trump posts wild AI video throwing Stephen Colbert into a dumpster — The posting of AI-generated political satire by public figures challenges free speech norms and platform content moderation policies.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.AI updates on arXiv.org.