Automatic long-term deception detection in group interaction videos

Chongyang Bai, Maksim Bolonkin, Judee K Burgoon, Chao Chen, Norah Dunbar, Bharat Singh, V. S. Subrahmanian, Zhe Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
PublisherIEEE Computer Society
Pages1600-1605
Number of pages6
ISBN (Electronic)9781538695524
DOIs
StatePublished - Jul 1 2019
Event2019 IEEE International Conference on Multimedia and Expo, ICME 2019 - Shanghai, China
Duration: Jul 8 2019Jul 12 2019

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2019-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2019 IEEE International Conference on Multimedia and Expo, ICME 2019
CountryChina
CityShanghai
Period7/8/197/12/19

Keywords

  • Deception detection
  • Media understanding
  • Multimodal analysis

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Bai, C., Bolonkin, M., Burgoon, J. K., Chen, C., Dunbar, N., Singh, B., ... Wu, Z. (2019). Automatic long-term deception detection in group interaction videos. In Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019 (pp. 1600-1605). [8784892] (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2019-July). IEEE Computer Society. https://doi.org/10.1109/ICME.2019.00276

Automatic long-term deception detection in group interaction videos. / Bai, Chongyang; Bolonkin, Maksim; Burgoon, Judee K; Chen, Chao; Dunbar, Norah; Singh, Bharat; Subrahmanian, V. S.; Wu, Zhe.

Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019. IEEE Computer Society, 2019. p. 1600-1605 8784892 (Proceedings - IEEE International Conference on Multimedia and Expo; Vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bai, C, Bolonkin, M, Burgoon, JK, Chen, C, Dunbar, N, Singh, B, Subrahmanian, VS & Wu, Z 2019, Automatic long-term deception detection in group interaction videos. in Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019., 8784892, Proceedings - IEEE International Conference on Multimedia and Expo, vol. 2019-July, IEEE Computer Society, pp. 1600-1605, 2019 IEEE International Conference on Multimedia and Expo, ICME 2019, Shanghai, China, 7/8/19. https://doi.org/10.1109/ICME.2019.00276
Bai C, Bolonkin M, Burgoon JK, Chen C, Dunbar N, Singh B et al. Automatic long-term deception detection in group interaction videos. In Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019. IEEE Computer Society. 2019. p. 1600-1605. 8784892. (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2019.00276
Bai, Chongyang ; Bolonkin, Maksim ; Burgoon, Judee K ; Chen, Chao ; Dunbar, Norah ; Singh, Bharat ; Subrahmanian, V. S. ; Wu, Zhe. / Automatic long-term deception detection in group interaction videos. Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019. IEEE Computer Society, 2019. pp. 1600-1605 (Proceedings - IEEE International Conference on Multimedia and Expo).
@inproceedings{59727085e3be42fc9d9e25ed43fe446e,
title = "Automatic long-term deception detection in group interaction videos",
abstract = "Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting.",
keywords = "Deception detection, Media understanding, Multimodal analysis",
author = "Chongyang Bai and Maksim Bolonkin and Burgoon, {Judee K} and Chao Chen and Norah Dunbar and Bharat Singh and Subrahmanian, {V. S.} and Zhe Wu",
year = "2019",
month = "7",
day = "1",
doi = "10.1109/ICME.2019.00276",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",
pages = "1600--1605",
booktitle = "Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019",

}

TY - GEN

T1 - Automatic long-term deception detection in group interaction videos

AU - Bai, Chongyang

AU - Bolonkin, Maksim

AU - Burgoon, Judee K

AU - Chen, Chao

AU - Dunbar, Norah

AU - Singh, Bharat

AU - Subrahmanian, V. S.

AU - Wu, Zhe

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting.

AB - Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting.

KW - Deception detection

KW - Media understanding

KW - Multimodal analysis

UR - http://www.scopus.com/inward/record.url?scp=85071007381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071007381&partnerID=8YFLogxK

U2 - 10.1109/ICME.2019.00276

DO - 10.1109/ICME.2019.00276

M3 - Conference contribution

AN - SCOPUS:85071007381

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

SP - 1600

EP - 1605

BT - Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019

PB - IEEE Computer Society

ER -