Effective methods for evaluating the reliability of statements issued by witnesses and defendants in hearings would be an extremely valuable support to decision-making in court and other legal settings. In recent years, methods relying on stylometric techniques have proven most successful for this task; but few such methods have been tested with language collected in real-life situations of high-stakes deception, and therefore their usefulness outside lab conditions still has to be properly assessed. In this study we report the results (...) obtained by using stylometric techniques to identify deceptive statements in a corpus of hearings collected in Italian courts. The defendants at these hearings were condemned for calumny or false testimony, so the falsity of (some of) their statements is fairly certain. In our experiments we replicated the methods used in previous studies but never before applied to high-stakes data, and tested new methods. We also considered the effect of a number of variables including in particular the homogeneity of the dataset. Our results suggest that accuracy at deception detection clearly above chance level can be obtained with real-life data as well. (shrink)

Deception is a reasonably common part of daily life that society sometimes demonstrates a degree of acceptance of, and occasionally people are very willing to be deceived. But can a computer identify deception and distinguish it from that which is not deceptive? We explore deception in various guises, differentiating it from lies, and highlighting the influence of medium and message in both deception and its detection. Our investigations to date have uncovered disagreements relating to the (...) measurements of such cues, and variations in interpretations, as could be problematic in building a deception detection system. (shrink)

Geven, Ben‐Shakhar, Kindt and Verschuere point out that research on deception detection usually employs instructed cheating. They experimentally demonstrate that participants show slower reaction times for concealed information than for other information, regardless of whether they are explicitly instructed to cheat or whether they can freely choose to cheat or not. Finding this ‘cognitive signature of lying’ with self‐initiated cheating too is argued by the authors to strengthen the external validity of deception detection research. [75].

The ability to detect deception is one of the most intriguing features of our minds. Cognitive load can surprisingly increase the accuracy of detection when there is a substantial load compared to when the detection is performed without cognitive load. This effect was tested in two experiments. In the first experiment, the participants were asked to watch truth/lie videos while completing a concurrent task (N‐back in a 3‐back version; intuitive processing), providing verbal reasoning after watching each video (...) (deliberative processing), or watching the videos alone (control group). The cognitive load caused by the concurrent task led to a higher accuracy in deception detection compared to the other conditions. In the second experiment, we examined how this effect worked under various amounts of cognitive load. Participants watching truth/lie videos were assigned to one of three experimental conditions (N‐back in three versions: 1, 3, and 5‐back) or to a control group. The participants in the 3‐back and 5‐back conditions exhibited a significantly higher accuracy in deception detection than those in the 1‐back and control groups. Thus, the effect of increased accuracy in deception detection is due to cognitive load and is related to the amount of cognitive load present. (shrink)

Linguistic Deception Detection DD is a well-established part of forensic linguistics and an area that continues to attract attention on the part of researchers, self-styled experts, and the public at large. In this article, the various approaches to DD within the general field of linguistics are examined. The basic method is to treat language as a form of behaviour and to equate marked linguistic behaviour with other marked forms of behaviour. Such a comparison has been identified in other (...) fields such as psychology and kinesics as being associated with stress linked to the attempt to deceive, typically in such contexts as examined here. Representative authentic examples of some of the most common linguistic indicators of deception that have been identified are discussed, dividing them into two general categories which we here introduce: language as revealer and language as concealer. We will argue that linguistic analysis for DD should be conducted relative to the subject’s individual linguistic patterns of behaviour, not on absolutes related to broad generalisations about what is supposedly normal or unmarked in the population at large. We will also briefly discuss some structured methods for linguistic analysis for DD and the prospect that technology and artificial intelligence will provide the means to automate and digitalise the linguistic DD process. We maintain that caution is advisable when considering these, as DD will, in all probability, always remain a work in progress, with the need for a flexible human evaluator ready to take into account many different aspects of the individual subject and the case in question. (shrink)

Research in the psychology of deception detection implies that Fricker, in making her case for reductionism in the epistemology of testimony, overestimates both the epistemic demerits of the antireductionist policy of trusting speakers blindly and the epistemic merits of the reductionist policy of monitoring speakers for trustworthiness: folk psychological prejudices to the contrary notwithstanding, it turns out that monitoring is on a par (in terms both of the reliability of the process and of the sensitivity of the beliefs (...) that it produces) with blind trust. The consequence is that while (a version of) Fricker’s argument for the necessity of a reduction succeeds, her argument for the availability of reductions fails. This does not, however, condemn us to endorse standard pessimistic reductionism, according to which there is no testimonial knowledge, for recent research concerning the methods used by subjects to discover deception in non-laboratory settings suggests that only a more moderate form of pessimism is in order. (shrink)

Neuroimaging technologies have improved our understanding of deception and also exhibit their potential in revealing the origins of its neural mechanism. In this study, a quantitative power analysis method that uses the Welch power spectrum estimation of functional near-infrared spectroscopy signals was proposed to examine the brain activation difference between the spontaneous deceptive behavior and controlled behavior. The power value produced by the model was applied to quantify the activity energy of brain regions, which can serve as a neuromarker (...) for deception detection. Interestingly, the power analysis results generated from the Welch spectrum estimation method demonstrated that the spontaneous deceptive behavior elicited significantly higher power than that from the controlled behavior in the prefrontal cortex. Meanwhile, the power findings also showed significant difference between the spontaneous deceptive behavior and controlled behavior, indicating that the reward system was only involved in the deception. The proposed power analysis method for processing fNIRS data provides us an additional insight to understand the cognitive mechanism of deception. (shrink)

The work presented here investigates the process by which one group of individuals solves the problem of detecting deceptions created by other agents. A field experiment was conducted in which twenty‐four auditors (partners in international public accounting firms) were asked to review four cases describing real companies that, unknown to the auditors, had perpetrated financial frauds. While many of the auditors failed to detect the manipulations in the cases, a small number of auditors were consistently successful. Since the detection (...) of frauds occurs infrequently in the work of a given auditor, we explain success by the application of powerful heuristics gained from experience with deceptions in everyday life. These heuristics implement a variation of Dennett's intentional stance strategy, which is based on interpreting detected inconsistencies in the light of the Deceiver's (i.e., management's) goals and possible actions. We explain failure to detect deception by means of perturbations (bugs) in the domain knowledge of accounting needed to apply these heuristics to the specific context of financial statement fraud. We test our theory by showing that a computational model of fraud detection that employs the proposed heuristics successfully detects frauds in the cases given to the auditors. We then modify the model by introducing perturbations based on the errors made by each of the auditors in the four cases. The resulting models account for 84 of the 96 observations (i.e., 24 auditors × four cases) in our data. (shrink)

The work presented here investigates the process by which one group of individuals solves the problem of detecting deceptions created by other agents. A field experiment was conducted in which twenty-four auditors (partners in international public accounting firms) were asked to review four cases describing real companies that, unknown to the auditors, had perpetrated financial frauds. While many of the auditors failed to detect the manipulations in the cases, a small number of auditors were consistently successful. Since the detection (...) of frauds occurs infrequently in the work of a given auditor, we explain success by the application of powerful heuristics gained from experience with deceptions in everyday life. These heuristics implement a variation of Dennett's intentional stance strategy, which is based on interpreting detected inconsistencies in the light of the Deceiver's (i.e., management's) goals and possible actions. We explain failure to detect deception by means of perturbations (bugs) in the domain knowledge of accounting needed to apply these heuristics to the specific context of financial statement fraud. We test our theory by showing that a computational model of fraud detection that employs the proposed heuristics successfully detects frauds in the cases given to the auditors. We then modify the model by introducing perturbations based on the errors made by each of the auditors in the four cases. The resulting models account for 84 of the 96 observations (i.e., 24 auditors × four cases) in our data. (shrink)

With the rapid growth of online product reviews, many users refer to others’ opinions before deciding to purchase any product. However, unfortunately, this fact has promoted the constant use of fake reviews, resulting in many wrong purchase decisions. The effective identification of deceptive reviews becomes a crucial yet challenging task in this research field. The existing supervised learning methods require a large number of labeled examples of deceptive and truthful opinions by domain experts, while the available unsupervised learning methods are (...) inefficient because they depend on the features of reviewers to detect each fake review. Therefore, by focusing on the detection efficiency problem and the limitation of large amount of labeled examples dependence, in this paper, we proposed an effective semisupervised learning approach for detecting spam reviews. Firstly, a time series model of all the reviews of a product is constructed, and then the suspected time intervals are captured based on the burst review increases in these intervals. Secondly, a co-training two-view semisupervised learning algorithm was performed in each captured interval, in which linguistic cues, metadata, and user purchase behaviors were synthetically employed to classify the reviews and check whether they are spam ones or not. A series of numerical experiments on a real dataset acquired from Taobao.com have confirmed the effectiveness of the proposed model, not only reaping benefits in terms of time efficiency and high accuracy but also overcoming the shortcomings of supervised learning methods, which depend on large amounts of labeled examples. And a trade-off balance was obtained between accuracy and efficiency. (shrink)

Compared to truthful answers, deceptive responses to queries are expected to take longer to initiate. Yet attempts to detect lies through reaction time (RT) have met with limited success. We describe a new procedure that seems to increase the RT difference between truth-telling and lies. It relies on a Stroop-like procedure in which responses to the labels true and false are sometimes reversed. The utility of this method is assessed in a laboratory study involving both statements of fact and attitude. (...) Three different ethnic groups participated: Americans of European ancestry, East Asians, and native Arabic speakers. For all three groups, our technique allowed identification of prevarication reliably better than chance. (shrink)

Dodging questions pervades human interaction, including interpersonal interactions, relational conversations, media interviews and political debates. Variously referred to as equivocation, evasion, obfuscation, strategic ambiguity and topic avoidance, among other terms, the concept has a rich history in the communication literature. Covertly dodging questions presents serious social and political problems. This essay focuses on theoretical issues of dodging, specifically the ability for a person to change the subject with an irrelevant answer. Discussion primarily draws upon Grice’s theory of conversational implicature and (...) deception research inspired by Grice. Theoretical impediments to detecting dodges are discussed, as well as barriers to accuracy from the perspective of discourse analysts and societal perceptions. (shrink)

I find three major shortcomings in Mele's account. First, verbal ambiguities suggest that the analysis is irrelevant to self-deception and/or that the traditional conception is subtly reinstated. Second, the data offer no means of establishing the superiority of the present account. Finally, as political rhetoric, Mele's proposal not only operates to disqualify others, but establishes science as their judge.

It is widespread that the consumers browse relevant reviews for reference before purchasing the products when online shopping. Some stores or users may write deceptive reviews to mislead consumers into making risky purchase decisions. Existing methods of deceptive review detection did not consider the valid product review sets and classification probability of feature weights. In this research, we propose a deceptive review detection algorithm based on the target product identification and the calculation of the Metapath feature weight, noted (...) as TM-DRD. The review dataset of target product is modeled as a heterogeneous review information network with the feature nodes. The classification method of graph is used to detect the deceptive reviews, which can improve the efficiency and accuracy of deceptive review detection due to the sparsity, imbalance of deceptive reviews, and the absence of category probability of feature weight calculation. The TM-DRD algorithm we proposed is validated on the real review dataset Yelp and compared with the SpEagle, NFC, and NetSpam algorithm. The experiment results demonstrate that the TM-DRD algorithm performs better than the other method with regard to the accuracy and efficiency. (shrink)

The present cross-sectional study (N = 205) tested the hypothesis that the Dark Triad traits – narcissism, Machiavellianism, and psychopathy – and the PID-5 maladaptive personality traits – Negative Affectivity, Detachment, Antagonism, Disinhibition and Psychoticism – are associated with specific deception-related perceptions: perceived cue-based deception detectability, perceived deception production, and deception detection ability. Participants completed personality and deception measures in an online setting. All three Dark Triad traits and Antagonism were associated with perceived (...) class='Hi'>deception production ability, but not (substantially) with perceived deception detection ability and cue-based deception detectability. The results provide a more fine-grained picture of biases associated with the Dark Triad traits in the context of deception and further support the relevance of Antagonism and Detachment as deception relevant personality traits. (shrink)

Misleading information pervades marketing communications, and is a long-standing issue in business ethics. Regulators place a heavy burden on consumers to detect misleading information, and a number of studies have shown training can improve their ability to do so. However, the possible side effects have largely gone unexamined. We provide evidence for one such side-effect, whereby training consumers to detect a specific tactic (illegitimate endorsers), leaves them more vulnerable to a second tactic included in the same ad (a restrictive qualifying (...) footnote), relative to untrained controls. We update standard notions of persuasion knowledge using a goal systems approach that allows for multiple vigilance goals to explain such side-effects in terms of goal shielding, which is a generally adaptive process by which activation and/or fulfillment of a low-level goal inhibits alternative detection goals. Furthermore, the same goal systems logic is used to develop a more general form of training that activates a higher-level goal (general skepticism). This more general training improved detection of a broader set of tactics without the negative goal shielding side effect. (shrink)

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) built for specific competitive situations, and general-purpose AI systems (such as large language models). Next, we detail several risks from AI deception, such as fraud, election (...) tampering, and losing control of AI systems. Finally, we outline several potential solutions to the problems posed by AI deception: first, regulatory frameworks should subject AI systems that are capable of deception to robust risk-assessment requirements; second, policymakers should implement bot-or-not laws; and finally, policymakers should prioritize the funding of relevant research, including tools to detect AI deception and to make AI systems less deceptive. Policymakers, researchers, and the broader public should work proactively to prevent AI deception from destabilizing the shared foundations of our society. (shrink)

This article synthesizes research presented in several models of unethical behavior to develop propositions about the factors that facilitate and mitigate deception in online business communications. The work expands the social network perspective to incorporate the medium of communication as a significant influence on deception. We go beyond existing models by developing seven propositions that identify how social network and issue moral intensity characteristics influence the probability of deception in online business communication in comparison to traditional communication (...) channels. Remedies to detect and discourage deception in online business networks are also offered, as well as limitations and future research directions. (shrink)

The recent emergence of machine-manipulated media raises an important societal question: How can we know whether a video that we watch is real or fake? In two online studies with 15,016 participants, we present authentic videos and deepfakes and ask participants to identify which is which. We compare the performance of ordinary human observers with the leading computer vision deepfake detection model and find them similarly accurate, while making different kinds of mistakes. Together, participants with access to the model’s (...) prediction are more accurate than either alone, but inaccurate model predictions often decrease participants’ accuracy. To probe the relative strengths and weaknesses of humans and machines as detectors of deepfakes, we examine human and machine performance across video-level features, and we evaluate the impact of preregistered randomized interventions on deepfake detection. We find that manipulations designed to disrupt visual processing of faces hinder human participants’ performance while mostly not affecting the model’s performance, suggesting a role for specialized cognitive capacities in explaining human deepfake detection performance. -/- . (shrink)

People are typically poor at telling apart truthful and deceptive statements. Based on the Unconscious Thought Theory, it has been suggested that poor lie detection arises from the intrinsic limitations of conscious thinking and can be improved by facilitating the contribution of unconscious thought. In support of this hypothesis, Reinhard, Greifeneder, and Scharmach (2013) observed improved lie detection among participants engaging in unconscious thought. The present study aimed to replicate this unconscious thought advantage using a similar experimental procedure (...) but with an important improvement in a key control condition. Specifically, participants judged the truthfulness of 8 video recordings in three thinking modes: immediately after watching them or after a period of unconscious or conscious deliberation. Results from two experiments (combined N = 226) failed to reveal a significant difference in lie detection accuracy between the thinking modes, even after efforts were made to facilitate the occurrence of an unconscious thought advantage in Experiment 2. The results imply that the unconscious thought advantage in deception detection is not a robust phenomenon. (shrink)

We examine deceptive impression management's effect on a supervisor's ratings of promotability and relationship quality (i.e., leader-member exchange) via the mediating role of the supervisor's recognition of deception. Extending ego depletion theory using social information processing theory, we argue that deceptive impression management in a supervisor-subordinate relationship is difficult to accomplish and the degree that deception is detected will negatively impact desired outcomes. Data collected from a matched sample of 171 public sector employees and their supervisors supported this (...) model and indicated that recognition fully mediated the negative relationships between deceptive impression management with supervisor's rating of promotability and relationship quality. (shrink)

Facial expressions of emotion play an important role in human social interactions. However, posed expressions of emotion are not always the same as genuine feelings. Recent research has found that facial expressions are increasingly used as a tool for understanding social interactions instead of personal emotions. Therefore, the credibility assessment of facial expressions, namely, the discrimination of genuine (spontaneous) expressions from posed (deliberate/volitional/deceptive) ones, is a crucial yet challenging task in facial expression understanding. With recent advances in computer vision and (...) machine learning techniques, rapid progress has been made in recent years for automatic detection of genuine and posed facial expressions. This paper presents a general review of the relevant research, including several spontaneous vs. posed (SVP) facial expression databases and various computer vision based detection methods. In addition, a variety of factors that will influence the performance of SVP detection methods are discussed along with open issues and technical challenges in this nascent field. (shrink)

Detection of deception and confirmation of truth telling with conventional polygraphy raised a host of technical and ethical issues. Recently, newer methods of recording electromagnetic signals from the brain show promise in permitting the detection of deception or truth telling. Some are even being promoted as more accurate than conventional polygraphy. While the new technologies raise issues of personal privacy, acceptable forensic application, and other social issues, the focus of this paper is the technical limitations of (...) the developing technology. Those limitations include the measurement validity of the new technologies, which remains largely unknown. Another set of questions pertains to the psychological paradigms used to model or constrain the target behavior. Finally, there is little standardization in the field, and the vulnerability of the techniques to countermeasures is unknown. Premature application of these technologies outside of research settings should be resisted, and the social conversation about the appropriate parameters of its civil, forensic, and security use should begin. (shrink)

The prevalence of sensationalized headlines and deceptive narratives in online content has prompted the need for effective clickbait detection methods. This study delves into the nuances of clickbait in Hebrew, scrutinizing diverse features such as linguistic and structural features, and exploring various types of clickbait in Hebrew, a language that has received relatively limited attention in this context. Utilizing a range of machine learning models, this research aims to identify linguistic features that are instrumental in accurately classifying Hebrew headlines (...) as either clickbait or non-clickbait. The findings underscore the critical role of linguistic attributes in enhancing the performance of the classification model. Notably, the employment of a machine learning model resulted in an impressive accuracy of 0.87 in clickbait detection. Moving forward, our research plan encompasses dataset expansion through the best machine learning model assisted labelling, with the objective of optimizing deep learning models for even more robust outcomes. This study not only advances clickbait detection in the realm of Hebrew but also emphasizes the fundamental importance of linguistic features in the accurate classification of clickbait. (shrink)

Detection of deception and confirmation of truth telling with conventional polygraphy raised a host of technical and ethical issues. Recently, newer methods of recording electromagnetic signals from the brain show promise in permitting the detection of deception or truth telling. Some are even being promoted as more accurate than conventional polygraphy. While the new technologies raise issues of personal privacy, acceptable forensic application, and other social issues, the focus of this paper is the technical limitations of (...) the developing technology. Those limitations include the measurement validity of the new technologies, which remains largely unknown. Another set of questions pertains to the psychological paradigms used to model or constrain the target behavior. Finally, there is little standardization in the field, and the vulnerability of the techniques to countermeasures is unknown. Premature application of these technologies outside of research settings should be resisted, and the social conversation about the appropriate parameters of its civil, forensic, and security use should begin. (shrink)

This paper examines several issues regarding deception in advertising. Some generally accepted definitions are considered and found to be inadequate. An alternative definition is proposed for legal/regulatory purposes and is related to a suggested definition of the term deception as it is used in everyday language. Based upon these definitions, suggestions are offered for detecting and regulating deception in advertising. This paper additionally considers the grounds for the generally held but largely unquestioned assumption that deceptive advertising is (...) unethical. It is argued that deceptive advertising can be shown to be morally objectionable, on the weak assumption that it is prima facie wrong to harm others. Finally, the implications of this analysis with respect to current regulation of deceptive advertising by the FTC are considered. (shrink)

This article describes key paradigms employed to assess deception and reviews the main neuroscience-based technologies that have been employed to investigate the neural correlates of deception: electroencephalography, functional magnetic resonance imaging, and transcranial direct current stimulation. Any potential use of neuroscience-based methods to detect deception in real-life situations requires successful classification in single subjects. It describes findings on the single subject performance of these methods and addresses the effects of two factors that are problematic for all (...) class='Hi'>deception detection methods, the potential use of countermeasures, strategies used by subjects to defeat the deception detection tests, and the potential role of false memories and of incidental encoding. It briefly outlines some of the ethical issues associated with these technologies to detect deceptive behavior. (shrink)

Deception is an all-too-common human activity, one that succeeds because we cannot always detect it in others. It complicates all sorts of human decision-making, including attributing guilt for criminal offenses. The law relies on human fact-finders to determine whether criminal defendants claiming innocence, as well as witnesses testifying about a case, are telling the truth. But the fallibility of human lie detection has fueled the search for a more accurate replacement. Scientists have developed new approaches to lie (...) class='Hi'>detection that use a brain scanning technique called functional magnetic resonance imaging (fMRI) to evaluate whether someone is lying. In experimental settings, researchers have found .. (shrink)