Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes
A new study published on arXiv explores how different humor styles and topics affect human perception of jokes delivered by AI robots. Researchers found that humor type significantly impacts how funny a joke is perceived, with aggressive and affiliative humor scoring higher. The content of the joke, specifically whether it was person-related or political, primarily influenced its appropriateness, with person-related jokes being favored. Language preference was also observed to be influenced by joke content and the participants' own language fluency and humor practices. AI
IMPACT This research could inform the development of more socially adept AI agents capable of nuanced humor in human-robot interactions.