What's the Deal with Robot Comedy? Pinpointing the Impact of Post-Joke Repartee in a Robotic Comedian's Performance
Ayan Robinson, Sarah Woods, Madison Shippy, DeAndre Walcott, Naomi T. Fitter
AI summary
Problem
Social robots currently lack the ability to effectively adapt their humor to human reactions, leaving a gap in understanding whether context-aware banter actually enhances interactions. This paper investigates whether adaptive post-joke repartee improves human responses compared to hardcoded or no repartee.
Approach
We conducted two studies comparing human responses to a Misty II robot delivering jokes under three conditions: no repartee, hardcoded repartee, and adaptive repartee driven by real-time facial expression classification.
Key results
- Any robot repartee significantly increased positive facial reactions compared to no repartee
- Adaptive repartee tended to yield higher warmth and competence ratings, but differences were not statistically significant
- Online survey confirmed any repartee boosted perceived competence and anthropomorphism while increasing discomfort
- Published reusable performance scripts and clarified that adaptive banter is not an unconditional improvement over hardcoded quips
Why it matters
Provides actionable insights for robotics practitioners and HCI researchers designing playful, context-aware banter to enhance social robot charm and interaction success.
Abstract
The rise in prevalence of AI-enabled technologies (from voice assistants to social robots) has not yet been accom- panied by an analogous mastery of computer-mediated humor. Although humans often use jokes to repair interactions and navigate uncomfortable scenarios, social robots in similar roles typically fall short at reading the room and adapting behavior according to sensed social contexts and reactions. We pursued two studies to gain clearer evidence about adaptive robot joking’s influence (compared to hardcoded repartee or no robot banter). The first study (N = 48, between-subjects design) examined in-person one-on-one human-robot interactions across the three conditions. The results indicated that adaptive repartee by robots tended to increase perceived warmth, competence, comfort, social closeness feelings, and humorousness, and that human behavioral responses varied significantly between conditions, with any repartee leading to significant gains over no repartee. The second study used an online video-based survey with a within- subjects design (N = 99) to examine the same conditions. This follow-up effort showed significant gains in perceived competence and anthropomorphism for any type of repartee, although this banter also made the robot more discomforting. Our work can help practitioners who are interested in applying playful banter to enhance robot charm and success.