Exploring Humor as a Repair Strategy During Communication Breakdowns with Voice Assistants
Authors
Voice assistants are becoming increasingly useful and support realistic conversations, yet communication breakdowns occur. We investigate the use of humor as a repair strategy in an experiment where the voice assistant makes a mistake and then utilizes one of four humorous personalities to repair the breakdown in the conversation. We conducted a study with 30 participants, each of whom took the Humor Style Questionnaire (HSQ) to understand their predisposition to humor type, and then engaged in conversation with each of the four humorous personalities and one that was designed to give neutral repair responses (non-humorous). Aggressive personalities were rated as the funniest, yet there was no clear connection between the participant's humor style and their preferred voice assistant personality. While humorous responses were successful in repairing communication breakdowns, participants overall preferred non-humorous responses. This research provides insight into the role of humor in communication breakdown repair with voice assistants.
Research Questions / Practical Problems
Question signals indexed for this paper.
Research Questions
3- During communication breakdowns with voice assistants, can humorous repair strategies improve user experience?Category: Dialogue Error Repair and Failure Recovery StrategiesSimilar questionsarrow_forward
- Which humor types (e.g., affiliative, self-enhancing) are most effective in voice assistant communication repair?Category: Dialogue Error Repair and Failure Recovery StrategiesSimilar questionsarrow_forward
- How do humorous repair strategies affect users' satisfaction, perceived intelligence, and likability of voice assistants?Category: Dialogue Error Repair and Failure Recovery StrategiesSimilar questionsarrow_forward
Practical Problems
1- When communication breaks down, voice assistants easily frustrate users and lack humanized feedback.Category: Dialogue Error Repair and Failure Recovery StrategiesSimilar questionsarrow_forward
- 100%
Emotional Dialogue Generation Using Image-Grounded Language Models
CHI '18· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
Understanding Affective Experiences with Conversational Agents
CHI '19· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
A New Uncanny Valley? The Effects of Speech Fidelity and Human Listener Gender on Social Perceptions of a Virtual-Human Speaker
CHI '22· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
Simulating Human Imprecision in Temporal Statements of Intelligent Virtual Agents
CHI '22· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
Super Kawaii Vocalics: Amplifying the “Cute” Factor in Computer Voice
CHI '25· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
“Hello, This is a Voice Assistant Calling" When a Human Voice Calls Claiming to Be a Machine on an Ordinary Day
DIS '25· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
Typing Behavior is About More than Speed: Users' Strategies for Choosing Word Suggestions Despite Slower Typing Rates
MobileHCI '23· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 100%
Agent-based Mediation on Smartphone Usage among Co-located Couples
MobileHCI '24· Intelligent Voice Assistants (Alexa, Siri, etc.) +1
- 67%
Implicit Communication of Actionable Information in Human-AI teams
CHI '19· Intelligent Voice Assistants (Alexa, Siri, etc.) +2
- 67%
What Do We See in Them? Identifying Dimensions of Partner Models for Speech Interfaces Using a Psycholexical Approach
CHI '21· Voice User Interface (VUI) Design +2
Based on Jaccard similarity of research subtopics & professions (≥60%)