Deception Detection Research Articles

A Registered Conceptual Replication and Extension of Carter and Weber (2010): Generalized Trust, Lie Prevalence, and Deception Detection

This paper provides a conceptual replication and extension of Carter and Weber investigating the effects of generalized trust on deception detection. Three alternative predictions were tested: trust lowers accuracy, trust increases accuracy, or trust facilitates accuracy for truths but inhibits lie detection. Compared to Carter and Weber, our experiment involved different stimulus materials, a much larger sample, and the inclusion of a lie prevalence measure. As anticipated, Carter and Weber’s finding were not replicated. Neither generalized trust nor lie prevalence predicted deception detection accuracy or truth bias. We speculate about why generalized trust appears to play little role in deception detection.

Deception Detection: Using Machine Learning to Analyze 911 Calls.

This study examined the use of machine learning in detecting deception among 210 individuals reporting homicides or missing persons to 911. The sample included an equal number of false allegation callers (FAC) and true report callers (TRC) identified through case adjudication. Independent coders, unaware of callers' deception, analyzed each 911 call using 86 behavioral cues. Using the random forest model with k-fold cross-validation and repeated sampling, the study achieved an accuracy rate of 68.2% for all 911 calls, with sensitivity and specificity at 68.7% and 67.7%, respectively. For homicide reports, accuracy was higher at 71.2%, with a sensitivity of 77.3% but slightly lower specificity at 65.0%. In contrast, accuracy decreased to 61.4% for missing person reports, with a sensitivity of 49.1% and notably higher specificity at 73.6%. Beyond accuracy, key cues distinguishing FACs from TRCs were identified and included cues like "Blames others," "Is self-dramatizing," and "Is uncertain and insecure."

Does (Biasing) Nonverbal Information Deteriorate the Accuracy of the Take‐the‐Best Heuristic for Deception Detection?

ABSTRACTPeople are poor lie detectors, partly because they hold false beliefs about nonverbal cues to deception. Here, we investigated if guiding people to rely only on a message's detailedness (“take‐the‐best”) boosts their lie detection and to what extent such heuristic judgments are immune to nonverbal information. In three studies (Ns = 109, 88 and 144), participants made detailedness‐based veracity judgements, of text versus video statements (Study 1), or of statements without or with biasing nonverbal behavior (truth tellers diverting, liars maintaining gaze; Studies 2 and 3). Compared to unguided judgements, participants using the heuristic method achieved higher deception detection accuracy throughout. Mere access to nonverbal behavior did not deteriorate performance (Study 1), but the heuristic was not fully immune to biasing nonverbal behavior (Studies 2, 3). Our findings challenge the lay notion that access to nonverbal behavior benefits deception detection and suggest that only focusing on diagnostic cues improves lie detection.

Statistical Analysis of Video Databases for Deception Detection Tasks

Statistical Analysis of Video Databases for Deception Detection Tasks

(MIS)measuring cognitive load and arousal in deception: A multitrait–multimethod analysis

AbstractPurposeCognitive load and arousal are cornerstones of many deception detection strategies and theories; in turn, their effective measurement is critical. However, fundamental criteria for establishing the quality and accuracy of measures have largely been overlooked. In this study, we examined the reliability and construct validity of common cognitive load and arousal measures.MethodWe obtained three independent secondary datasets in which participants (N = 238) had lied or told the truth about witnessing a suspicious event. Using a multitrait–multimethod analysis, we assessed three measures of their cognitive load and arousal: participants' self‐reports, trained coders' observations, and objective behaviours.ResultsAlthough all measures were reliable, they achieved differing levels of validation. Specifically, measures of cognitive load showed evidence of convergent validity, but not discriminant validity. There was no empirical support for the construct validity of arousal measures.ConclusionsThese findings suggest that inconsistencies in the diagnosticity of cues to deception and theory support may be attributable to the measures employed. Researchers may not be assessing constructs of interest, particularly in the case of arousal.

Infrared thermal imaging and eye-tracking for deception detection: a laboratory study

Infrared thermal imaging and eye-tracking for deception detection: a laboratory study

A knowledge-Aware NLP-Driven conversational model to detect deceptive contents on social media posts

The widespread dissemination of deceptive content on social media presents a substantial challenge to preserving authenticity and trust. The epidemic growth of false news is due to the greater use of social media to transmit news, rather than conventional mass media such as newspapers, magazines, radio, and television. Humans' incapacity to differentiate among true and false facts exposes fake news as a threat to logical truth, democracy, journalism, and government credibility. Using combination of advanced methodologies, Deep learning (DL) methods, and Natural Language Processing (NLP) approaches, researchers and technology developers attempt to make robust systems proficient in discerning the subtle nuances that betray deceptive intent. Analysing conversational linguistic patterns of misleading data, these techniques’ purpose to progress the resilience of social platforms against the spread of deceptive content, eventually contributing to an additional informed and trustworthy online platform. This paper proposed a Knowledge-Aware NLP-Driven AlBiruni Earth Radius Optimization Algorithm with Deep Learning Tool for Enhanced Deceptive Content Detection (BER-DLEDCD) algorithm on Social Media. The purpose of the BER-DLEDCD system is to identify and classify the existence of deceptive content utilizing NLP with optimal DL model. In the BER-DLEDCD technique, data pre-processing takes place to change the input data into compatible format. Furthermore, the BER-DLEDCD approach applies hybrid DL technique encompassing Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) methodology for deceptive content detection. Moreover, the BER approach has been deployed to boost hyperparameter choice of the CNN-LSTM technique which leads to enhanced detection performance. The simulation outcome of the BER-DLEDCD system has been examined employing benchmark database. The extensive outcomes stated the BER-DLEDCD system achieved excellent performance with the accuracy of 94 %, 94.83 % precision, 94.30 % F-score with other recent approaches.

How political consultants can leverage partisan media combativeness in the U.S.

ABSTRACT The growth of partisan media presents new challenges for political consultants. Informed by social identity theory and truth-default theory, this paper examines how U.S. voters react to politicians in combative news interviews. Experiment 1 (N = 320) establishes that an ingroup politician gains more trust among ingroup voters when interviewed by cross-partisan media accusing the politician of deception than when interviewed more congenially by co-partisan media. Experiment 2 (N = 131) finds that perceived media hostility increases Democrats’ and Republicans’ trust in a politician regardless of whether the interviewer accuses the politician of deception or is congenial. Experiment 3 (N = 126) replicates the findings when a Democrat is accused of deception on Fox News. The study tested a moderated mediation model, finding that Republican and Democratic voters do not react differently in the process. The discussion highlights the practical and theoretical implications of hostile media perceptions and ingroup–outgroup partisan bias in a polarized media environment with conflicting exposure to live fact-checking and deception detection.

Deceptive evidence detection of belief functions based on reinforcement learning in partial label environment

Counter-deception evidence fusion is a critical issue in the application of Dempster-Shafer Theory (DST). Effectively detecting deceptive evidence poses a significant challenge in DST-based information fusion. Existing research on this topic is limited and often lacks a clear distinction between deceptive and trustworthy evidence. Recently, two explicit definitions of deceptive evidence have been proposed to address different scenarios: one for cases with label information and another for cases without. However, these definitions are somewhat counter-intuitive and do not address situations where partial label information is available.To address this gap, our paper introduces a new, explicit definition of deceptive evidence that considers both the characteristics of the evidence and the fusion system. This definition encompasses cases including with label information, without label information, and with partial label information. It extends the two previously mentioned definitions and, in certain circumstances, aligns with them.Based on our new definition, we propose a mathematical model for counter-deception evidence fusion across these three scenarios and apply reinforcement learning to solve it. We present several numerical simulations, a data-driven counter-deception test, and a practical application to demonstrate that our method outperforms previous approaches in both detecting deceptive evidence and in practical applications, showcasing superior effectiveness and robustness.

Collaboration, crowdsourcing, and misinformation.

One of humanity's greatest strengths lies in our ability to collaborate to achieve more than we can alone. Just as collaboration can be an important strength, humankind's inability to detect deception is one of our greatest weaknesses. Recently, our struggles with deception detection have been the subject of scholarly and public attention with the rise and spread of misinformation online, which threatens public health and civic society. Fortunately, prior work indicates that going beyond the individual can ameliorate weaknesses in deception detection by promoting active discussion or by harnessing the "wisdom of crowds." Can group collaboration similarly enhance our ability to recognize online misinformation? We conducted a lab experiment where participants assessed the veracity of credible news and misinformation on social media either as an actively collaborating group or while working alone. Our results suggest that collaborative groups were more accurate than individuals at detecting false posts, but not more accurate than a majority-based simulated group, suggesting that "wisdom of crowds" is the more efficient method for identifying misinformation. Our findings reorient research and policy from focusing on the individual to approaches that rely on crowdsourcing or potentially on collaboration in addressing the problem of misinformation.

Automated Comparative Predictive Analysis of Deception Detection in Convicted Offenders Using Polygraph with Random Forest, Support Vector Machine, and Artificial Neural Network Models

Automated Comparative Predictive Analysis of Deception Detection in Convicted Offenders Using Polygraph with Random Forest, Support Vector Machine, and Artificial Neural Network Models

Interoceptive Accuracy Enhances Deception Detection in Older Adults.

Difficulties with deception detection may leave older adults especially vulnerable to fraud. Interoception, i.e., the awareness of one's bodily signals, has been shown to influence deception detection, but this relationship has not been examined in aging yet. The present study investigated effects of interoceptive accuracy on two forms of deception detection: detecting interpersonal lies in videos and identifying text-based deception in phishing emails. Younger (18-34 years) and older (53-82 years) adults completed a heartbeat-detection task to determine interoceptive accuracy. Deception detection was assessed across two distinct, ecologically valid tasks: i) a lie detection task in which participants made veracity judgments of genuine and deceptive individuals, and ii) a phishing email detection task to capture online deception detection. Using multilevel logistic regression models, we determined the effect of interoceptive accuracy on lie and phishing detection in younger versus older adults. In older, but not younger, adults greater interoceptive accuracy was associated with better accuracy in both detecting deceptive people and phishing emails. Interoceptive accuracy was associated with both lie detection and phishing detection accuracy among older adults. Our findings identify interoceptive accuracy as a potential protective factor for fraud susceptibility, as measured through difficulty detecting deception. These results support interoceptive accuracy as a relevant factor for consideration in interventions targeted at fraud prevention among older adults.

EEG-based deception detection using weighted dual perspective visibility graph analysis

EEG-based deception detection using weighted dual perspective visibility graph analysis

A Review of Attacker–Defender Games and Cyber Security

The focus of this review is the long and broad history of attacker–defender games as a foundation for the narrower and shorter history of cyber security. The purpose is to illustrate the role of game theory in cyber security and which areas have received attention and to indicate future research directions. The methodology uses the search terms game theory, attack, defense, and cyber security in Web of Science, augmented with the authors’ knowledge of the field. Games may involve multiple attackers and defenders over multiple periods. Defense involves security screening and inspection, the detection of invaders, jamming, secrecy, and deception. Incomplete information is reviewed due to its inevitable presence in cyber security. The findings pertain to players sharing information weighted against the security investment, influenced by social planning. Attackers stockpile zero-day cyber vulnerabilities. Defenders build deterrent resilient systems. Stochastic cyber security games play a role due to uncertainty and the need to build probabilistic models. Such games can be further developed. Cyber security games based on traffic and transportation are reviewed; they are influenced by the more extensive communication of GPS data. Such games should be extended to comprise air, land, and sea. Finally, cyber security education and board games are reviewed, which play a prominent role.

Parsing communication duration and diagnostic question effects in deception detection

ABSTRACT An experiment (N = 155) testing mere duration and diagnostic content hypotheses in deception detection is reported. To the extent that observable behavioral cues aid deception detection, longer behavioral samples may provide a greater opportunity for cues to emerge, thereby increasing accuracy relative to the observation of short snippets of interviews. In contrast, truth-default theory proposes that question-and-answer content is a moderator, and more is only better when questions prompt diagnostic communication content. A 2 × 2 experiment varied communication duration (short, long) and questioning approach (more, less diagnostic). Consistent with the diagnostic content hypothesis, the results suggest that duration only mattered within the more diagnostic question condition. In the less diagnostic question condition, the results mirrored prior meta-analysis regardless of duration. The findings align with truth-default theory and provide evidence for a theory-based approach to improving deception detection.

Self and other-perceived deception detection abilities are highly correlated but unassociated with objective detection ability: Examining the detection consensus effect

Subjective lying rates are often strongly and positively correlated. Called the deception consensus effect, people who lie often tend to believe others lie often, too. The present paper evaluated how this cognitive bias also extends to deception detection. Two studies (Study 1: N = 180 students; Study 2: N = 250 people from the general public) had participants make 10 veracity judgments based on videotaped interviews, and also indicate subjective detection abilities (self and other). Subjective, perceived detection abilities were significantly linked, supporting a detection consensus effect, yet they were unassociated with objective detection accuracy. More overconfident detectors—those whose subjective detection accuracy was greater than their objective detection accuracy—reported telling more white and big lies, cheated more on a behavioral task, and were more ideologically conservative than less overconfident detectors. This evidence supports and extends contextual models of deception (e.g., the COLD model), highlighting possible (a)symmetries in subjective and objective veracity assessments.

Well done! Or how to Avoid Dangers of Pseudoscience: Common Standard for Research in Behavioural Analysis and Deception Detection in Aviation Security

Well done! Or how to Avoid Dangers of Pseudoscience: Common Standard for Research in Behavioural Analysis and Deception Detection in Aviation Security

Eyes do not lie but words do

Abstract Evidentiality encodes how a speaker has access to the information contained in his/her proposition. It has been shown that some ‘evidential language’ speakers make a deliberate choice of evidentials while telling lies (Aikhenvald 2004). In this study, we recruited 40 native speakers of Turkish, an ‘evidential language’, to judge statements with evidentials using an eye-movement-monitoring-during-reading study with an end-of-sentence deception detection task. The participants read sentences with four conditions, containing a direct or indirect evidential form either compatible or incompatible with the given information source. Our results show that the indirect evidential condition was detected as a lie more often than the direct evidential condition. Readers had the tendency to judge stimulus material with source-evidentiality mismatch to be untruthful. These findings were mirrored in the eye-movement data, as we found gaze duration to be longer at the critical verb region for indirect evidential and mismatch conditions.

Lay person’s and psychology officers’ beliefs about memory, investigative interviewing and deception detection: data from Malaysia

ABSTRACT It is very typical for people to think that the understanding of psychological phenomena is a matter of common sense. In many parts of the world, the general public and even some professional groups, often express commonly held beliefs about topics in psychology that are not in line with up-to-date scientific literature. To date, comparable data from Malaysia is lacking. In this study, 101 psychology officers serving the Ministry of Home Affairs as well as 130 student and community members in Malaysia completed a survey on beliefs about human memory, detecting lies and police interviews. Generally, participants possessed beliefs that were not in line with current psychological research, which is consistent with findings from many parts of the world. This study serves as an important gauge of the advancement of the field in this region.

A Handful of Remarks on the “Terminology Reference for the Science of Psychophysiological Detection of Deception”

A Handful of Remarks on the “Terminology Reference for the Science of Psychophysiological Detection of Deception”