High-Stakes Deception Detection Based on Facial Expressions

2014 ◽  
Author(s):  
Lin Su ◽  
Martin D. Levine
Keyword(s):  
Facial Expressions ◽  
Deception Detection ◽  
High Stakes

scholarly journals Sitting in judgment: How body posture influences deception detection and gazing behavior

2019 ◽  
Author(s):  
Mircea Zloteanu ◽  
Daniel C. Richardson
Keyword(s):  
Visual Attention ◽  
Facial Expressions ◽  
Nonverbal Behavior ◽  
Visual Information ◽  
Deception Detection ◽  
Body Posture ◽  
Gaze Behavior ◽  
High Stakes ◽  
Body Postures ◽  
The Way

Body postures can affect how we process and attend to information. Here, a novel effect of adopting an open or closed posture on the ability to detect deception was investigated. It was hypothesized that the posture adopted by decoders would affect their social acuity, resulting in differences in the detection of nonverbal behavior and discrimination of deceptive and truthful statements. In Study 1, adopting an open posture produced higher accuracy for detecting naturalistic lies, but no difference in the recognition of brief facial expressions, as compared to adopting a closed posture. Study 2 measured differences in gaze behavior based on posture when detecting both low and high stakes lies. Sitting in an open posture reduced visual attention towards senders, and in particular, the attention given to their hands. The findings suggest that simply shifting posture can impact veracity judgments and the way they attend to visual information.

scholarly journals Sitting in Judgment: How Body Posture Influences Deception Detection and Gazing Behavior

2021 ◽  
Vol 11 (6) ◽  
pp. 85
Author(s):  
Mircea Zloteanu ◽  
Eva G. Krumhuber ◽  
Daniel C. Richardson
Keyword(s):  
Facial Expressions ◽  
Nonverbal Behavior ◽  
Visual Information ◽  
Deception Detection ◽  
Body Posture ◽  
Additive Effect ◽  
Eye Tracker ◽  
High Stakes ◽  
Body Postures ◽  
Trait Empathy

Body postures can affect how we process and attend to information. Here, a novel effect of adopting an open or closed posture on the ability to detect deception was investigated. It was hypothesized that the posture adopted by judges would affect their social acuity, resulting in differences in the detection of nonverbal behavior (i.e., microexpression recognition) and the discrimination of deceptive and truthful statements. In Study 1, adopting an open posture produced higher accuracy for detecting naturalistic lies, but no difference was observed in the recognition of brief facial expressions as compared to adopting a closed posture; trait empathy was found to have an additive effect on posture, with more empathic judges having higher deception detection scores. In Study 2, with the use of an eye-tracker, posture effects on gazing behavior when judging both low-stakes and high-stakes lies were measured. Sitting in an open posture reduced judges’ average dwell times looking at senders, and in particular, the amount and length of time they focused on their hands. The findings suggest that simply shifting posture can impact judges’ attention to visual information and veracity judgments (Mg = 0.40, 95% CI (0.03, 0.78)).

scholarly journals Leaked Expressions Captured with Wearable High Resolution Facial Electromyography

2021 ◽  
Author(s):  
Yael Hanein
Keyword(s):  
Facial Expressions ◽  
High Speed ◽  
Emotional State ◽  
Deception Detection ◽  
Internal State ◽  
Electrode Array ◽  
Human Communication ◽  
Facial Electromyography ◽  
Video Recordings ◽  
Sensitive Tool

Facial-expressions play a major role in human communication and provide a window to an individual’s emotional state. While facial expressions can be consciously manipulated to conceal true emotions, very brief leaked expressions may occur, exposing one’s true internal state. Leaked expressions are therefore considered as an important hallmark in deception detection, a field with enormous social and economic impact. Challengingly, capturing these subtle and brief expressions has been so far limited to visual examination (manual or machine-based), with almost no electromyography evidence. In this investigation we set to explore whether electromyography of leaked expressions can be faithfully recorded with specially designed wearable electrodes. Indeed, using soft multi-electrode array based facial electromyography, we were able to record localized and brief signals in individuals instructed to suppress smiles. The electromyography evidence was validated with high-speed video recordings. The recording approach reported here provides a new and sensitive tool for leaked expression investigations and a basis for improved automated systems.

scholarly journals When the Body Knows: Interoceptive Accuracy Enhances Physiological But Not Explicit Differentiation Between Liars and Truth-Tellers

2021 ◽  
Author(s):  
Christopher Albert Gunderson ◽  
Leanne ten Brinke ◽  
Peter Sokol-Hessner
Keyword(s):  
Deception Detection ◽  
The Body ◽  
Physiological Reactivity ◽  
Detection Accuracy ◽  
Emotional Stimuli ◽  
High Stakes ◽  
Judgment Accuracy ◽  
Bodily Experiences ◽  
Interoceptive Accuracy ◽  
Physiological Reactions

Recent research suggests that people experience distinct physiological reactions to lies versus truths. It is unclear, however, if this experience is incorporated into greater truth-lie judgment accuracy. We hypothesized individuals with high interoceptive accuracy—those with greater access to bodily experiences and stronger physiological responses to emotional stimuli—might be particularly likely to accurately discriminate high-stakes, emotional lies and truths. Participants (n = 71) completed two study sessions: the first assessed their interoceptive accuracy with heartbeat detection measures and the second assessed their deception detection ability while measuring their physiological reactivity. Interoceptive accuracy was associated with a greater difference in vasoconstriction to liars (vs. truth-tellers), suggesting that interoception was positively associated with physiological sensitivity to deception. Interoceptive accuracy, however, was unrelated to deception detection accuracy. While better interoception provides enhanced physiological signals that could better discriminate lies from truths, it does not improve deception detection accuracy.

scholarly journals The Effect of Task-Irrelevant Emotional Valence on Limited Attentional Resources During Deception: An ERPs Study

2021 ◽  
Vol 15 ◽  
Author(s):  
Jing Liang ◽  
Qian-Nan Ruan ◽  
Ke-Ke Fu ◽  
Yu-Hsin Chen ◽  
Wen-Jing Yan
Keyword(s):  
Facial Expressions ◽  
Cognitive Processes ◽  
Deception Detection ◽  
Emotional Valence ◽  
Emotional Information ◽  
Attentional Resources ◽  
Emotional Processes ◽  
Dyadic Process ◽  
Task Irrelevant

Deception is a complex and cognitively draining dyadic process that simultaneously involves cognitive and emotional processes, both of which demand/capture attentional resources. However, few studies have investigated the allocation of attentional resources between cognitive and emotional processes during deception. The current study presented facial expressions of different valences to 36 participants. While an electroencephalogram was recording, they were asked to make either truthful or deceptive gender judgments according to preceding cues. The results showed that deceptive responses induced smaller P300 amplitudes than did truthful responses. Task-irrelevant negative emotional information (TiN) elicited larger P300 amplitudes than did task-irrelevant positive emotional information (TiP). Furthermore, the results showed that TiN elicited larger LPP amplitudes than did TiP in deceptive responses, but not in truthful ones. The results suggested that attentional resources were directed away to deception-related cognitive processes and TiN, but not TiP, was consistently able to compete for and obtain attentional resources during deception. The results indicated that TiN could disrupt with deception and may facilitate deception detection.

The Connection Between Deception Detection and Financial Exploitation of Older (vs. Young) Adults

2021 ◽  
pp. 073346482110497
Author(s):  
Christopher A. Gunderson ◽  
Leanne ten Brinke
Keyword(s):  
Young Adults ◽  
Deception Detection ◽  
Future Research ◽  
Detection Accuracy ◽  
High Stakes ◽  
Cross Sectional ◽  
Factors Affecting ◽  
Financial Exploitation ◽  
Financial Consequences ◽  
Cross Sectional Design

Although poor deception detection accuracy is thought to be an important risk factor for fraud among older adults, this link has not been explicitly studied. Using a cross-sectional design, older and young adults viewed and made judgments of real, high-stakes truths and lies with financial consequences. Older (vs. young) adults exhibited a greater truth bias when evaluating individuals pleading for help in finding a missing relative, which was associated with greater donations to deceptive pleaders. However, all participants were highly vulnerable to fraud. Future research should consider both risk and protective factors affecting financial fraud across the lifespan.

scholarly journals Catching a Liar Through Facial Expression of Fear

2021 ◽  
Vol 12 ◽  
Author(s):  
Xunbing Shen ◽  
Gaojie Fan ◽  
Caoyuan Niu ◽  
Zhencai Chen
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Time Window ◽  
Total Duration ◽  
Truth Telling ◽  
High Stakes ◽  
Game Show ◽  
Facial Movements ◽  
Video Clips ◽  
The Moment

High stakes can be stressful whether one is telling the truth or lying. However, liars can feel extra fear from worrying to be discovered than truth-tellers, and according to the “leakage theory,” the fear is almost impossible to be repressed. Therefore, we assumed that analyzing the facial expression of fear could reveal deceits. Detecting and analyzing the subtle leaked fear facial expressions is a challenging task for laypeople. It is, however, a relatively easy job for computer vision and machine learning. To test the hypothesis, we analyzed video clips from a game show “The moment of truth” by using OpenFace (for outputting the Action Units (AUs) of fear and face landmarks) and WEKA (for classifying the video clips in which the players were lying or telling the truth). The results showed that some algorithms achieved an accuracy of >80% merely using AUs of fear. Besides, the total duration of AU20 of fear was found to be shorter under the lying condition than that from the truth-telling condition. Further analysis found that the reason for a shorter duration in the lying condition was that the time window from peak to offset of AU20 under the lying condition was less than that under the truth-telling condition. The results also showed that facial movements around the eyes were more asymmetrical when people are telling lies. All the results suggested that facial clues can be used to detect deception, and fear could be a cue for distinguishing liars from truth-tellers.

Sign in / Sign up

Export Citation Format

Share Document