Do Liars Blink Differently?: Automated Blink Detection during Deceptive Interviews

Aaron C. Elkins; Nikolaos Sorros; Stefanos Zafeiriou; Judee K. Burgoon; Maja  Pantic; Jay F. Nunamaker

Do Liars Blink Differently? Automated Blink Detection during Deceptive Interviews

Aaron C. Elkins, Nikolaos Sorros, Stefanos Zafeiriou, Judee K. Burgoon, Maja Pantic, Jay F. Nunamaker

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1316 Downloads (Pure)

Abstract

This research investigates the development and use of an automated blink detection algorithm applied to a large (N=176) deceptive interview video corpus. The automated blink detection algorithm was 93% accurate. This work represents the first analysis of deceptive blinks of this magnitude (46 hours of video) and degree of ecological validity. After applying the algorithm to the interview video corpus, deceivers were found to blink less when lying to cognitively demanding questions. In addition to deception, people blinked more over time, more when older, and less when more skilled in social expressivity. The results of this study suggest that any deception detection algorithm that relies on blinks needs to account for time, interviewee demographics and social skill, question type, and turn taking phase (interviewee listening r speaking).

Original language	English
Title of host publication	Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium
Subtitle of host publication	January 2014
Editors	Matthew Jensen, Thomas Meservy, Judee Burgoon, Jay Nunamaker
Number of pages	7
Publication status	Published - 6 Jan 2014
Externally published	Yes
Event	HICSS-47 Rapid Screening Technologies, Deception Detection Credibility Assessment Symposium 2014 - Hilton Waikoloa, Big Island, United States Duration: 6 Jan 2014 → 7 Jan 2014

Conference

Conference	HICSS-47 Rapid Screening Technologies, Deception Detection Credibility Assessment Symposium 2014
Country/Territory	United States
City	Big Island
Period	6/01/14 → 7/01/14

Access to Document

HICSS47_Do Liars Blink DifferentlyFinal published version, 194 KB

Cite this

@inproceedings{08ca7ad804ee4f40a2ac52f749c2de3e,

title = "Do Liars Blink Differently?: Automated Blink Detection during Deceptive Interviews",

abstract = "This research investigates the development and use of an automated blink detection algorithm applied to a large (N=176) deceptive interview video corpus. The automated blink detection algorithm was 93% accurate. This work represents the first analysis of deceptive blinks of this magnitude (46 hours of video) and degree of ecological validity. After applying the algorithm to the interview video corpus, deceivers were found to blink less when lying to cognitively demanding questions. In addition to deception, people blinked more over time, more when older, and less when more skilled in social expressivity. The results of this study suggest that any deception detection algorithm that relies on blinks needs to account for time, interviewee demographics and social skill, question type, and turn taking phase (interviewee listening r speaking).",

author = "Elkins, {Aaron C.} and Nikolaos Sorros and Stefanos Zafeiriou and Burgoon, {Judee K.} and Maja Pantic and Nunamaker, {Jay F.}",

year = "2014",

month = jan,

day = "6",

language = "English",

editor = "Matthew Jensen and Thomas Meservy and Judee Burgoon and Jay Nunamaker",

booktitle = "Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium",

note = "HICSS-47 Rapid Screening Technologies, Deception Detection Credibility Assessment Symposium 2014 ; Conference date: 06-01-2014 Through 07-01-2014",

}

Elkins, AC, Sorros, N, Zafeiriou, S, Burgoon, JK, Pantic, M & Nunamaker, JF 2014, Do Liars Blink Differently? Automated Blink Detection during Deceptive Interviews. in M Jensen, T Meservy, J Burgoon & J Nunamaker (eds), Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium: January 2014. HICSS-47 Rapid Screening Technologies, Deception Detection Credibility Assessment Symposium 2014, Big Island, Hawaii, United States, 6/01/14.

Do Liars Blink Differently? Automated Blink Detection during Deceptive Interviews. / Elkins, Aaron C.; Sorros, Nikolaos; Zafeiriou, Stefanos et al.
Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium: January 2014. ed. / Matthew Jensen; Thomas Meservy; Judee Burgoon; Jay Nunamaker. 2014.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Do Liars Blink Differently?

T2 - HICSS-47 Rapid Screening Technologies, Deception Detection Credibility Assessment Symposium 2014

AU - Elkins, Aaron C.

AU - Sorros, Nikolaos

AU - Zafeiriou, Stefanos

AU - Burgoon, Judee K.

AU - Pantic, Maja

AU - Nunamaker, Jay F.

PY - 2014/1/6

Y1 - 2014/1/6

N2 - This research investigates the development and use of an automated blink detection algorithm applied to a large (N=176) deceptive interview video corpus. The automated blink detection algorithm was 93% accurate. This work represents the first analysis of deceptive blinks of this magnitude (46 hours of video) and degree of ecological validity. After applying the algorithm to the interview video corpus, deceivers were found to blink less when lying to cognitively demanding questions. In addition to deception, people blinked more over time, more when older, and less when more skilled in social expressivity. The results of this study suggest that any deception detection algorithm that relies on blinks needs to account for time, interviewee demographics and social skill, question type, and turn taking phase (interviewee listening r speaking).

AB - This research investigates the development and use of an automated blink detection algorithm applied to a large (N=176) deceptive interview video corpus. The automated blink detection algorithm was 93% accurate. This work represents the first analysis of deceptive blinks of this magnitude (46 hours of video) and degree of ecological validity. After applying the algorithm to the interview video corpus, deceivers were found to blink less when lying to cognitively demanding questions. In addition to deception, people blinked more over time, more when older, and less when more skilled in social expressivity. The results of this study suggest that any deception detection algorithm that relies on blinks needs to account for time, interviewee demographics and social skill, question type, and turn taking phase (interviewee listening r speaking).

M3 - Conference contribution

BT - Proceedings of the Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium

A2 - Jensen, Matthew

A2 - Meservy, Thomas

A2 - Burgoon, Judee

A2 - Nunamaker, Jay

Y2 - 6 January 2014 through 7 January 2014

ER -

Do Liars Blink Differently? Automated Blink Detection during Deceptive Interviews

Abstract

Conference

Access to Document

Fingerprint

Cite this