Graduate Thesis Or Dissertation


Toward Machine Learning-Enabled Adaptivity for Humorous Robots Public Deposited

Downloadable Content

Download PDF


Attribute NameValues
  • Social robots benefit from a sense of humor, which requires the ability to recognize and adapt to human responses during playful interactions. Past work on humorous robots has classified audience responses with audio-based and preliminary visual-based methods following the joke punchline. Building on this progress, we conducted a survey of 20 human comedians to inform the design of robotic comedians. Using the comedians’ insights, we designed an audio-based machine learning pipeline to detect joke enjoyment while the joke setup is being read as well as following the punchline. Furthermore, we used the Facial Action Coding System as the basis for a machine learning pipeline to detect joke enjoyment using participant faces in one-on-one interactions. Finally, we designed and evaluated a new robotic comedian system using the visual classifier. In this work, we present the comedian survey findings, joke enjoyment classification methods, and insights from the deployment of our robotic comedian. This work’s contributions to humor as a robotic social skill support the likability and acceptance of social robots.
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Committee Member
Academic Affiliation
Rights Statement
Peer Reviewed



This work has no parents.

In Collection: