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

2026-06-11 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Expert, quick

Summary

An exploratory study evaluated AI-generated jokes delivered by a robot in a university classroom, investigating how humor style, joke content, and language preference influence perceptions in human-robot interaction. Employing a mixed factorial design, researchers examined four humor types—Affiliative, Self-Enhancing, Aggressive, and Self-Defeating—and two joke content categories: person-related versus political. The study measured perceived funniness, appropriateness, and preferred language. Results indicate that humor type significantly impacts funniness, with Aggressive and Affiliative humor receiving higher ratings. Joke content primarily determined appropriateness, showing a preference for person-related jokes over political ones. Furthermore, language preference was influenced by both joke content and participants' self-reported fluency and humor practices. This research was published on 2026-06-11.

Key takeaway

For AI scientists developing humorous human-robot interaction, prioritize humor style over content for maximizing funniness. Focus on Aggressive or Affiliative humor types to elicit more laughter. Simultaneously, ensure joke content is person-related rather than political to maintain high appropriateness ratings. When designing multilingual humor, consider your audience's fluency and humor practices to optimize language selection and delivery.

Key insights

Aggressive and Affiliative humor styles enhance robot-delivered joke funniness, while person-related topics improve appropriateness.

Principles

• Humor style dictates funniness.
• Joke content shapes acceptability.
• Language preference is multi-faceted.

Method

A mixed factorial design evaluated AI-generated jokes delivered by a robot in a university classroom, assessing humor type and content effects on funniness, appropriateness, and language preference.

In practice

• Prioritize Aggressive/Affiliative humor for robots.
• Favor person-related joke content.
• Consider audience fluency for language.

Topics

• Computational Humor
• Human-Robot Interaction
• AI-Generated Jokes
• Humor Styles
• Joke Acceptability
• Bilingual AI

Best for: AI Scientist, Research Scientist

Related on AIssential

• Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes — Humor style dictates funniness, while joke topic determines acceptability for robot-delivered AI jokes.
• 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.
• AI is teaching us to speak like bots, and it’s a problem — AI chatbots are subtly homogenizing human language, making our communication increasingly machine-like by nudging expression towards an average.
• 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.
• Token-Level Pun Location Using Multi-Layer BERT with Mixture of Experts — A two-stage BERT-MoE model effectively locates puns in Portuguese by specializing expert components.
• Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages — Idiomatic expressions challenge multilingual NLP, with literal meanings and low-resource languages posing significant hurdles.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.