Oh F**k! How Do People Feel about Robots that Leverage Profanity? (2505.05831v1)

Abstract: Profanity is nearly as old as language itself, and cursing has become particularly ubiquitous within the last century. At the same time, robots in personal and service applications are often overly polite, even though past work demonstrates the potential benefits of robot norm-breaking. Thus, we became curious about robots using curse words in error scenarios as a means for improving social perceptions by human users. We investigated this idea using three phases of exploratory work: an online video-based study (N = 76) with a student pool, an online video-based study (N = 98) in the general U.S. population, and an in-person proof-of-concept deployment (N = 52) in a campus space, each of which included the following conditions: no-speech, non-expletive error response, and expletive error response. A surprising result in the outcomes for all three studies was that although verbal acknowledgment of an error was typically beneficial (as expected based on prior work), few significant differences appeared between the non-expletive and expletive error acknowledgment conditions (counter to our expectations). Within the cultural context of our work, the U.S., it seems that many users would likely not mind if robots curse, and may even find it relatable and humorous. This work signals a promising and mischievous design space that challenges typical robot character design.

• The paper investigates how people react to robots using profanity during error scenarios through online and in-person studies.
• Findings across multiple studies indicate that verbal error acknowledgments, including expletives, can increase perceived warmth, competence, humor, and relatability compared to silent robots.
• While profanity may enhance engagement and rapport in some contexts, the results also highlight the need for personalization and cultural sensitivity due to potential user discomfort.

Analyzing Human Reactions to Profane Robots in Service Application Contexts

The integration of robots into personal and service sectors prompts a myriad of considerations, including their embodiment, social behavior, and interaction protocols. Madison R. Shippy et al.'s paper "Oh F**k! How Do People Feel about Robots that Leverage Profanity?" presents an exploratory investigation into the social perceptions and acceptability of robots using expletive language during error scenarios. This topic examines the intersection of human-robot interaction (HRI), social norm violation, and emotional expression, contributing to the broader discourse on how robots are perceived in increasingly human-populated environments.

Investigative Framework

The researchers conducted three distinct studies to evaluate how people perceive robots that use profanity in error scenarios—an online video-based paper with a student participant pool, a follow-up online paper with a broader U.S. sample, and an in-person deployment at a university. Each paper involved the presentation of three conditions: no-speech control, non-expletive verbal error acknowledgment, and expletive verbal error acknowledgment using the Hello Robot Stretch RE2 mobile manipulator. The research design aimed to strike a balance between maintaining a degree of anthropomorphism while challenging traditional robot norm adherence.

Research Findings and Implications

The results of all three studies revealed several significant insights. In each phase, verbal acknowledgment of errors was associated with higher perceived warmth, competence, humorousness, anthropomorphism, and likability, compared to a no-speech reaction. Expletive responses, although set to reflect negative emotions, did not elicit stronger negative perceptions than expected; rather, the conditions elicited relatability and humor in many participants. In particular, the in-person deployment provided an immersive context revealing that verbal responses to errors—whether expletive or not—increased relatability and elicited laughter more compared to a silent robot.

The reported results contribute key design implications for roboticists: they highlight that utilizing expletive language in error reactions might not detract from a robot's likeability but instead enhance engagement and relatability. This finding challenges the traditional avoidance of norm-breaking behaviors in robots, suggesting a design space where mischief may pave the way for building rapport and social inclusion, depending on the context and cultural acceptance.

However, the research signals caution. Although some participants found the cursing humorous and relatable, others exhibited discomfort, especially where religiously-connotated swears were involved. This dichotomy indicates that expletive robots might benefit from personalization or explicit contextual limitation based on users' preferences and sensitivities. Culturally and contextually adaptive systems may optimize user experience, tailoring their expletive behavior to align with the individual's perceptions and environment.

Future Prospects in HRI Design

The paper paves the way for novel inquiries into robotic behavior design, emphasizing a nuanced "continuum of mischief" in HRI. Future research could expand across varied cultural contexts to assess broader acceptability and implications of profanity, probe into personalization techniques, and investigate long-term interaction effects over extended contexts. Additionally, research might explore the role of adaptive AI in optimizing the use of profanity based on real-time interaction feedback.

In summary, Shippy et al.'s work reinforces the notion that while traditional social norms should inform robot design, experimenting with deviations might offer unexpected benefits to HRI, especially in settings where engagement and relatability are of paramount importance. The prospects of profanity in robots warrant further exploration, promising to refine robots' roles as social entities in human-centric environments.