1
|
Loconte R, Russo R, Capuozzo P, Pietrini P, Sartori G. Verbal lie detection using Large Language Models. Sci Rep 2023; 13:22849. [PMID: 38129677 PMCID: PMC10739834 DOI: 10.1038/s41598-023-50214-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2023] [Accepted: 12/16/2023] [Indexed: 12/23/2023] Open
Abstract
Human accuracy in detecting deception with intuitive judgments has been proven to not go above the chance level. Therefore, several automatized verbal lie detection techniques employing Machine Learning and Transformer models have been developed to reach higher levels of accuracy. This study is the first to explore the performance of a Large Language Model, FLAN-T5 (small and base sizes), in a lie-detection classification task in three English-language datasets encompassing personal opinions, autobiographical memories, and future intentions. After performing stylometric analysis to describe linguistic differences in the three datasets, we tested the small- and base-sized FLAN-T5 in three Scenarios using 10-fold cross-validation: one with train and test set coming from the same single dataset, one with train set coming from two datasets and the test set coming from the third remaining dataset, one with train and test set coming from all the three datasets. We reached state-of-the-art results in Scenarios 1 and 3, outperforming previous benchmarks. The results revealed also that model performance depended on model size, with larger models exhibiting higher performance. Furthermore, stylometric analysis was performed to carry out explainability analysis, finding that linguistic features associated with the Cognitive Load framework may influence the model's predictions.
Collapse
Affiliation(s)
- Riccardo Loconte
- Molecular Mind Lab, IMT School for Advanced Studies Lucca, Piazza San Francesco 19, 55100, Lucca, LU, Italy.
| | - Roberto Russo
- Department of Mathematics "Tullio Levi-Civita", University of Padova, Padova, Italy
| | - Pasquale Capuozzo
- Department of General Psychology, University of Padova, Padova, Italy
| | - Pietro Pietrini
- Molecular Mind Lab, IMT School for Advanced Studies Lucca, Piazza San Francesco 19, 55100, Lucca, LU, Italy
| | - Giuseppe Sartori
- Department of General Psychology, University of Padova, Padova, Italy
| |
Collapse
|
2
|
Verschuere B, Lin CC, Huismann S, Kleinberg B, Willemse M, Mei ECJ, van Goor T, Löwy LHS, Appiah OK, Meijer E. The use-the-best heuristic facilitates deception detection. Nat Hum Behav 2023; 7:718-728. [PMID: 36941469 DOI: 10.1038/s41562-023-01556-2] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2022] [Accepted: 02/10/2023] [Indexed: 03/23/2023]
Abstract
Decades of research have shown that people are poor at detecting deception. Understandably, people struggle with integrating the many putative cues to deception into an accurate veracity judgement. Heuristics simplify difficult decisions by ignoring most of the information and relying instead only on the most diagnostic cues. Here we conducted nine studies in which people evaluated honest and deceptive handwritten statements, video transcripts, videotaped interviews or live interviews. Participants performed at the chance level when they made intuitive judgements, free to use any possible cue. But when instructed to rely only on the best available cue (detailedness), they were consistently able to discriminate lies from truths. Our findings challenge the notion that people lack the potential to detect deception. The simplicity and accuracy of the use-the-best heuristic provides a promising new avenue for deception research.
Collapse
Affiliation(s)
- Bruno Verschuere
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands.
| | - Chu-Chien Lin
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Sara Huismann
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Bennett Kleinberg
- Department of Methodology and Statistics, Tilburg University, Tilburg, the Netherlands
- Department of Security and Crime Science, University College London, London, UK
| | - Marleen Willemse
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Emily Chong Jia Mei
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Thierry van Goor
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Leonie H S Löwy
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Obed Kwame Appiah
- Department of Clinical Psychology, University of Amsterdam, Amsterdam, the Netherlands
| | - Ewout Meijer
- Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands
| |
Collapse
|
3
|
Constâncio AS, Tsunoda DF, Silva HDFN, da Silveira JM, Carvalho DR. Deception detection with machine learning: A systematic review and statistical analysis. PLoS One 2023; 18:e0281323. [PMID: 36757928 PMCID: PMC9910662 DOI: 10.1371/journal.pone.0281323] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Accepted: 01/20/2023] [Indexed: 02/10/2023] Open
Abstract
Several studies applying Machine Learning to deception detection have been published in the last decade. A rich and complex set of settings, approaches, theories, and results is now available. Therefore, one may find it difficult to identify trends, successful paths, gaps, and opportunities for contribution. The present literature review aims to provide the state of research regarding deception detection with Machine Learning. We followed the PRISMA protocol and retrieved 648 articles from ACM Digital Library, IEEE Xplore, Scopus, and Web of Science. 540 of them were screened (108 were duplicates). A final corpus of 81 documents has been summarized as mind maps. Metadata was extracted and has been encoded as Python dictionaries to support a statistical analysis scripted in Python programming language, and available as a collection of Jupyter Lab Notebooks in a GitHub repository. All are available as Jupyter Lab Notebooks. Neural Networks, Support Vector Machines, Random Forest, Decision Tree and K-nearest Neighbor are the five most explored techniques. The studies report a detection performance ranging from 51% to 100%, with 19 works reaching accuracy rate above 0.9. Monomodal, Bimodal, and Multimodal approaches were exploited and achieved various accuracy levels for detection. Bimodal and Multimodal approaches have become a trend over Monomodal ones, although there are high-performance examples of the latter. Studies that exploit language and linguistic features, 75% are dedicated to English. The findings include observations of the following: language and culture, emotional features, psychological traits, cognitive load, facial cues, complexity, performance, and Machine Learning topics. We also present a dataset benchmark. Main conclusions are that labeled datasets from real-life data are scarce. Also, there is still room for new approaches for deception detection with Machine Learning, especially if focused on languages and cultures other than English-based. Further research would greatly contribute by providing new labeled and multimodal datasets for deception detection, both for English and other languages.
Collapse
|
4
|
Brennen T, Magnussen S. The Science of Lie Detection by Verbal Cues: What Are the Prospects for Its Practical Applicability? Front Psychol 2022; 13:835285. [PMID: 35478762 PMCID: PMC9037296 DOI: 10.3389/fpsyg.2022.835285] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2021] [Accepted: 03/18/2022] [Indexed: 11/26/2022] Open
Abstract
There is agreement among researchers that no simple verbal cues to deception detectable by humans have been demonstrated. This paper examines the evidence for the most prominent current methods, critically considers the prevailing research strategy, proposes a taxonomy of lie detection methods and concludes that two common types of approach are unlikely to succeed. An approach to lie detection is advocated that derives both from psychological science and common sense: When an interviewee produces a statement that contradicts either a previous statement by the same person or other information the authorities have, it will in many cases be obvious to interviewer and interviewee that at least one of the statements is a lie and at the very least the credibility of the witness is reduced. The literature on Strategic Use of Evidence shows that features of interviews that foster such revelatory and self-trapping situations have been established to be a free account and the introduction of independent information late and gradually into the proceedings, and tactics based on these characteristics constitute the best current general advice for practitioners. If any other approach 1 day challenges this status quo, it is likely to be highly efficient automated systems.
Collapse
Affiliation(s)
- Tim Brennen
- Department of Psychology, University of Oslo, Oslo, Norway
| | | |
Collapse
|
5
|
Van Der Zee S, Poppe R, Havrileck A, Baillon A. A Personal Model of Trumpery: Linguistic Deception Detection in a Real-World High-Stakes Setting. Psychol Sci 2021; 33:3-17. [PMID: 34932410 DOI: 10.1177/09567976211015941] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Language use differs between truthful and deceptive statements, but not all differences are consistent across people and contexts, complicating the identification of deceit in individuals. By relying on fact-checked tweets, we showed in three studies (Study 1: 469 tweets; Study 2: 484 tweets; Study 3: 24 models) how well personalized linguistic deception detection performs by developing the first deception model tailored to an individual: the 45th U.S. president. First, we found substantial linguistic differences between factually correct and factually incorrect tweets. We developed a quantitative model and achieved 73% overall accuracy. Second, we tested out-of-sample prediction and achieved 74% overall accuracy. Third, we compared our personalized model with linguistic models previously reported in the literature. Our model outperformed existing models by 5 percentage points, demonstrating the added value of personalized linguistic analysis in real-world settings. Our results indicate that factually incorrect tweets by the U.S. president are not random mistakes of the sender.
Collapse
Affiliation(s)
- Sophie Van Der Zee
- Department of Applied Economics, Erasmus School of Economics, Erasmus University Rotterdam
| | - Ronald Poppe
- Department of Information and Computing Sciences, Utrecht University
| | - Alice Havrileck
- Department of Applied Economics, Erasmus School of Economics, Erasmus University Rotterdam.,Department of Economics and Management, École Normale Supérieure Paris-Saclay
| | - Aurélien Baillon
- Department of Applied Economics, Erasmus School of Economics, Erasmus University Rotterdam
| |
Collapse
|
6
|
Deeb H, Vrij A, Leal S, Mann S. Combining the model statement and the sketching while narrating interview techniques to elicit information and detect lies in multiple interviews. APPLIED COGNITIVE PSYCHOLOGY 2021. [DOI: 10.1002/acp.3880] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/14/2023]
Affiliation(s)
- Haneen Deeb
- Department of Psychology University of Portsmouth Portsmouth UK
| | - Aldert Vrij
- Department of Psychology University of Portsmouth Portsmouth UK
| | - Sharon Leal
- Department of Psychology University of Portsmouth Portsmouth UK
| | - Samantha Mann
- Department of Psychology University of Portsmouth Portsmouth UK
| |
Collapse
|
7
|
Kleinberg B, Verschuere B. How humans impair automated deception detection performance. Acta Psychol (Amst) 2021; 213:103250. [PMID: 33450692 DOI: 10.1016/j.actpsy.2020.103250] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2020] [Revised: 12/15/2020] [Accepted: 12/21/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Deception detection is a prevalent problem for security practitioners. With a need for more large-scale approaches, automated methods using machine learning have gained traction. However, detection performance still implies considerable error rates. Findings from different domains suggest that hybrid human-machine integrations could offer a viable path in detection tasks. METHOD We collected a corpus of truthful and deceptive answers about participants' autobiographical intentions (n = 1640) and tested whether a combination of supervised machine learning and human judgment could improve deception detection accuracy. Human judges were presented with the outcome of the automated credibility judgment of truthful or deceptive statements. They could either fully overrule it (hybrid-overrule condition) or adjust it within a given boundary (hybrid-adjust condition). RESULTS The data suggest that in neither of the hybrid conditions did the human judgment add a meaningful contribution. Machine learning in isolation identified truth-tellers and liars with an overall accuracy of 69%. Human involvement through hybrid-overrule decisions brought the accuracy back to chance level. The hybrid-adjust condition did not improve deception detection performance. The decision-making strategies of humans suggest that the truth bias - the tendency to assume the other is telling the truth - could explain the detrimental effect. CONCLUSIONS The current study does not support the notion that humans can meaningfully add the deception detection performance of a machine learning system. All data are available at https://osf.io/45z7e/.
Collapse
|
8
|
Lie-detection by strategy manipulation: Developing an asymmetric information management (AIM) technique. JOURNAL OF APPLIED RESEARCH IN MEMORY AND COGNITION 2020. [DOI: 10.1016/j.jarmac.2020.01.004] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
9
|
Forsyth L, Anglim J. Using text analysis software to detect deception in written short‐answer questions in employee selection. INTERNATIONAL JOURNAL OF SELECTION AND ASSESSMENT 2020. [DOI: 10.1111/ijsa.12284] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Loch Forsyth
- School of Psychology Deakin University Geelong Australia
| | - Jeromy Anglim
- School of Psychology Deakin University Geelong Australia
| |
Collapse
|
10
|
Bogaard G, van der Mark J, Meijer EH. Detecting false intentions using unanticipated questions. PLoS One 2019; 14:e0226257. [PMID: 31825997 PMCID: PMC6905579 DOI: 10.1371/journal.pone.0226257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2019] [Accepted: 11/23/2019] [Indexed: 11/19/2022] Open
Abstract
The present study investigated whether measurable verbal differences occur when people vocalize their true and false intentions. To test potential differences, we used an experimental set-up where liars planned a criminal act (i.e., installing a virus on a network computer) and truth-tellers a non-criminal act (i.e., installing a new presentation program "SlideDog" on a network computer). Before they could carry out these acts, a confederate intercepted the participant and interviewed them about their intentions and the planning phase by using both anticipated and unanticipated questions. Liars used a cover story to mask their criminal intentions while truth-tellers told the entire truth. In contrast to our hypotheses, both human and automated coding did not show any evidence that liars and truth-tellers differed in plausibility or detailedness. Furthermore, results showed that asking unanticipated questions resulted in lengthier answers than anticipated questions. These results are in line with the mixed findings in the intention literature and suggest that plausibility and detailedness are less diagnostic cues for deception about intentions.
Collapse
Affiliation(s)
- Glynis Bogaard
- Department of Clinical Psychological Science, Section Forensic Psychology, Maastricht University, Maastricht, The Netherlands
- * E-mail:
| | - Joyce van der Mark
- Department of Clinical Psychological Science, Section Forensic Psychology, Maastricht University, Maastricht, The Netherlands
| | - Ewout H. Meijer
- Department of Clinical Psychological Science, Section Forensic Psychology, Maastricht University, Maastricht, The Netherlands
| |
Collapse
|
11
|
Kleinberg B, Arntz A, Verschuere B. Being accurate about accuracy in verbal deception detection. PLoS One 2019; 14:e0220228. [PMID: 31393894 PMCID: PMC6687387 DOI: 10.1371/journal.pone.0220228] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2019] [Accepted: 07/01/2019] [Indexed: 11/19/2022] Open
Abstract
PURPOSE Verbal credibility assessments examine language differences to tell truthful from deceptive statements (e.g., of allegations of child sexual abuse). The dominant approach in psycholegal deception research to date (used in 81% of recent studies that report on accuracy) to estimate the accuracy of a method is to find the optimal statistical separation between lies and truths in a single dataset. However, this method lacks safeguards against accuracy overestimation. METHOD & RESULTS A simulation study and empirical data show that this procedure produces overoptimistic accuracy rates that, especially for small sample size studies typical of this field, yield misleading conclusions up to the point that a non-diagnostic tool can be shown to be a valid one. Cross-validation is an easy remedy to this problem. CONCLUSIONS We caution psycholegal researchers to be more accurate about accuracy and propose guidelines for calculating and reporting accuracy rates.
Collapse
Affiliation(s)
- Bennett Kleinberg
- Department of Security and Crime Science, University College London, London, United Kingdom
- Department of Psychology, University of Amsterdam, Amsterdam, The Netherlands
| | - Arnoud Arntz
- Department of Psychology, University of Amsterdam, Amsterdam, The Netherlands
| | - Bruno Verschuere
- Department of Psychology, University of Amsterdam, Amsterdam, The Netherlands
| |
Collapse
|
12
|
Leal S, Vrij A, Deeb H, Jupe L. Using the model statement to elicit verbal differences between truth tellers and liars: The benefit of examining core and peripheral details. JOURNAL OF APPLIED RESEARCH IN MEMORY AND COGNITION 2018. [DOI: 10.1016/j.jarmac.2018.07.001] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
13
|
Harvey AC, Vrij A, Sarikas G, Leal S, Jupe L, Nahari G. Extending the verifiability approach framework: The effect of initial questioning. APPLIED COGNITIVE PSYCHOLOGY 2018. [DOI: 10.1002/acp.3465] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Affiliation(s)
| | - Aldert Vrij
- Department of Psychology; University of Portsmouth; Portsmouth UK
| | - George Sarikas
- Department of Psychology; University of Portsmouth; Portsmouth UK
| | - Sharon Leal
- Department of Psychology; University of Portsmouth; Portsmouth UK
| | - Louise Jupe
- Department of Psychology; University of Portsmouth; Portsmouth UK
| | - Galit Nahari
- Department of Criminology; Bar-Ilan University; Ramat Gan Israel
| |
Collapse
|
14
|
Vrij A, Leal S, Fisher RP. Verbal Deception and the Model Statement as a Lie Detection Tool. Front Psychiatry 2018; 9:492. [PMID: 30356902 PMCID: PMC6190908 DOI: 10.3389/fpsyt.2018.00492] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/23/2018] [Accepted: 09/20/2018] [Indexed: 11/24/2022] Open
Abstract
We have been reliably informed by practitioners that police officers and intelligence officers across the world have started to use the Model Statement lie detection technique. In this article we introduce this technique. We describe why it works, report the empirical evidence that it works, and outline how to use it. Research examining the Model Statement only started recently and more research is required. We give suggestions for future research with the technique. The Model Statement technique is one of many recently developed verbal lie detection methods. We start this article with a short overview of the-in our view- most promising recent developments in verbal lie detection before turning our attention to the Model Statement technique.
Collapse
Affiliation(s)
- Aldert Vrij
- Department of Psychology, University of Portsmouth, Portsmouth, United Kingdom
| | - Sharon Leal
- Department of Psychology, University of Portsmouth, Portsmouth, United Kingdom
| | - Ronald P. Fisher
- Department of Psychology, Florida International University, Miami, FL, United States
| |
Collapse
|
15
|
Kleinberg B, Warmelink L, Arntz A, Verschuere B. The first direct replication on using verbal credibility assessment for the detection of deceptive intentions. APPLIED COGNITIVE PSYCHOLOGY 2018; 32:592-599. [PMID: 30333683 PMCID: PMC6174984 DOI: 10.1002/acp.3439] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2018] [Revised: 06/13/2018] [Accepted: 06/23/2018] [Indexed: 11/20/2022]
Abstract
Verbal deception detection has gained momentum as a technique to tell truth-tellers from liars. At the same time, researchers' degrees of freedom make it hard to assess the robustness of effects. Replication research can help evaluate how reproducible an effect is. We present the first replication in verbal deception research whereby ferry passengers were instructed to tell the truth or lie about their travel plans. The original study found truth-tellers to include more specific time references in their answers. The replication study that closely mimicked the setting, procedure, materials, coding, and analyses found no lie-truth difference for specific time references. Although the power of our replication study was suboptimal (0.77), Bayesian statistics showed evidence in favor of the null hypothesis. Given the great applied consequences of verbal credibility tests, we hope this first replication attempt ignites much needed preregistered, high-powered, multilab replication efforts.
Collapse
Affiliation(s)
- Bennett Kleinberg
- Department of PsychologyUniversity of AmsterdamAmsterdamThe Netherlands
| | | | - Arnoud Arntz
- Department of PsychologyUniversity of AmsterdamAmsterdamThe Netherlands
| | - Bruno Verschuere
- Department of PsychologyUniversity of AmsterdamAmsterdamThe Netherlands
| |
Collapse
|