Dissertation/Thesis Abstract

CIPHER: A Method for Constructing Autonomously Empathetic Systems Based on Contextual Human Behavior Interpretation and Falsifiable Event Prediction
by Buteau, Trevor Pierre, M.S., Fordham University, 2019, 103; 13427664
Abstract (Summary)

The prediction of internal human states—what a person is thinking and feeling—by computers remains an elusive yet attractive goal. The potential applications of such a system are many, including but not limited to lie detection, consumer satisfaction and interest, autonomous vehicle safety, enhanced social networking, and even robotic friendship and companionship.

We believe that scientific progress towards such lofty and exciting applications as described above has been slowed because prior efforts to create an autonomous computer system capable of predicting what a human being is thinking or feeling have been largely predicting or detecting “emotions” in humans, rather than detecting more empirically falsifiable events. There is much scholarly disagreement as to the exact nature of what emotions actually are, and thus Affective Computing dealing with emotional prediction is forced to rely on poorly-defined and often-contradictory ground truths.

In our research, we focus on predicting discrete events based on the expressive behavior of human subjects. Our systems use a user-dependent method of analysis and rely heavily on contextual information to make predictions about the meaning behind subject expressive behavior. Our system’s accuracy and therefore usefulness are built on provable ground truths that prohibit the drawing of inaccurate conclusions that other systems could too easily make.

While the current application of our research idea—a Contextually Informed Program for Hyper-personalized Empathetic Report, or CIPHER—is modest (predicting player behavior during a game of poker), we believe it to be the foundation upon which much more extensive empathetic and affective analysis systems could be solidly and eventually built.

Indexing (document details)
Advisor: Lyons, Damian
Commitee: Leeds, Daniel, Zhao, Yijun
School: Fordham University
Department: Computer and Information Science
School Location: United States -- New York
Source: MAI 58/04M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Psychology, Artificial intelligence, Computer science
Keywords: Affective computing, Computer vision, Contextual awareness, Event prediction, Machine learning, Poker
Publication Number: 13427664
ISBN: 978-0-438-96357-3
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest