Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language

© Springer International Publishing AG 2016. This paper investigates how an intelligent agent could be designed to both predict whether it is bonding with its user, and convey appropriate facial expression and body language responses to foster bonding. Video and Kinect recordings are collected from...

Full description

Bibliographic Details
Main Authors: Jaques, Natasha, McDuff, Daniel, Kim, Yoo Lim, Picard, Rosalind W.
Other Authors: Massachusetts Institute of Technology. Media Laboratory
Format: Article
Language:English
Published: Springer Nature America, Inc 2022
Online Access:https://hdl.handle.net/1721.1/138086.2
_version_ 1811084968781152256
author Jaques, Natasha
McDuff, Daniel
Kim, Yoo Lim
Picard, Rosalind W.
author2 Massachusetts Institute of Technology. Media Laboratory
author_facet Massachusetts Institute of Technology. Media Laboratory
Jaques, Natasha
McDuff, Daniel
Kim, Yoo Lim
Picard, Rosalind W.
author_sort Jaques, Natasha
collection MIT
description © Springer International Publishing AG 2016. This paper investigates how an intelligent agent could be designed to both predict whether it is bonding with its user, and convey appropriate facial expression and body language responses to foster bonding. Video and Kinect recordings are collected from a series of naturalistic conversations, and a reliable measure of bonding is adapted and verified. A qualitative and quantitative analysis is conducted to determine the non-verbal cues that characterize both high and low bonding conversations. We then train a deep neural network classifier using one minute segments of facial expression and body language data, and show that it is able to accurately predict bonding in novel conversations.
first_indexed 2024-09-23T13:00:55Z
format Article
id mit-1721.1/138086.2
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T13:00:55Z
publishDate 2022
publisher Springer Nature America, Inc
record_format dspace
spelling mit-1721.1/138086.22024-08-09T19:35:54Z Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language Jaques, Natasha McDuff, Daniel Kim, Yoo Lim Picard, Rosalind W. Massachusetts Institute of Technology. Media Laboratory © Springer International Publishing AG 2016. This paper investigates how an intelligent agent could be designed to both predict whether it is bonding with its user, and convey appropriate facial expression and body language responses to foster bonding. Video and Kinect recordings are collected from a series of naturalistic conversations, and a reliable measure of bonding is adapted and verified. A qualitative and quantitative analysis is conducted to determine the non-verbal cues that characterize both high and low bonding conversations. We then train a deep neural network classifier using one minute segments of facial expression and body language data, and show that it is able to accurately predict bonding in novel conversations. 2022-01-07T17:16:12Z 2021-11-09T21:49:10Z 2022-01-07T17:16:12Z 2016 2019-07-31T16:17:23Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/138086.2 Jaques, Natasha, McDuff, Daniel, Kim, Yoo Lim and Picard, Rosalind W. 2016. "Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language." en https://dx.doi.org/10.1007/978-3-319-47665-0_6 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/octet-stream Springer Nature America, Inc MIT web domain
spellingShingle Jaques, Natasha
McDuff, Daniel
Kim, Yoo Lim
Picard, Rosalind W.
Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title_full Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title_fullStr Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title_full_unstemmed Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title_short Understanding and Predicting Bonding in Conversations Using Thin Slices of Facial Expressions and Body Language
title_sort understanding and predicting bonding in conversations using thin slices of facial expressions and body language
url https://hdl.handle.net/1721.1/138086.2
work_keys_str_mv AT jaquesnatasha understandingandpredictingbondinginconversationsusingthinslicesoffacialexpressionsandbodylanguage
AT mcduffdaniel understandingandpredictingbondinginconversationsusingthinslicesoffacialexpressionsandbodylanguage
AT kimyoolim understandingandpredictingbondinginconversationsusingthinslicesoffacialexpressionsandbodylanguage
AT picardrosalindw understandingandpredictingbondinginconversationsusingthinslicesoffacialexpressionsandbodylanguage