Catch: Injecting "Contextual And Timely Conversational Humor" Into Lifelike Avatars

Abstract

Humor is an integral part of human interaction. In the same way that humor aids human conversation in a variety of situations, humor can also enable avatars to communicate with humans in a human-like manner. We investigated the technical feasibility of incorporating humor into lifelike avatars by developing CATCH, a humor engine module that can inject contextually appropriate and well-timed humor into an avatar's neutral response. CATCH examines contextual cues to select the most relevant humor for the situation and it dynamically determines when humor is appropriate via a laughter feedback system. Our experimental results indicate that CATCH consistently picks contextually appropriate humor on a balanced humor frequency and that humor increases the perceived human-likeness of our avatar.

Publication Date

1-1-2016

Publication Title

Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016

Number of Pages

134-139

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

85003819773 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85003819773

This document is currently not available here.

Share

COinS