Use of mouse-tracking software to detect faking-good behavior on personality questionnaires: an explorative study

Do privacy assurances work? a study of truthfulness in healthcare history data collection

Patients often provide untruthful information about their health to avoid embarrassment, evade treatment, or prevent financial loss. Privacy disclosures (e.g. HIPAA) intended to dissuade privacy concerns may actually increase patient lying. We used new mouse tracking-based technology to detect lies through mouse movement (distance and time to response) and patient answer adjustment in an online controlled study of 611 potential patients, randomly assigned to one of six treatments. Treatments differed in the notices patients received before health information was requested, including notices about privacy, benefits of truthful disclosure, and risks of inaccurate disclosure. Increased time or distance of device mouse movement and greater adjustment of answers indicate less truthfulness. Mouse tracking revealed a significant overall effect (p<0.001) by treatment on the time to reach their final choice. The control took the least time indicating greater truthfulness and the privacy + risk group took the longest indicating least truthfulness. Privacy, risk, and benefit disclosure statements led to greater lying. These differences were moderated by gender. Mouse tracking results largely confirmed the answer adjustment lie detection method with an overall treatment effect (p < .0001) and gender differences (p < .0001) on truthfulness. Privacy notices led to decreased patient honesty. Privacy notices should perhaps be administered well before personal health disclosure is requested to minimize patient untruthfulness. Mouse tracking and answer adjustment appear to be health care lie-detection methods to enhance optimal diagnosis and treatment.

Hands-on false memories: a combined study with distributional semantics and mouse-tracking

Although mouse-tracking has been seen as a real-time window into different aspects of human decision-making processes, currently little is known about how the decision process unfolds in veridical and false memory retrieval. Here, we directly investigated decision-making processes by predicting participants' performance in a mouse-tracking version of a typical Deese-Roediger-McDermott (DRM) task through distributional semantic models, a usage-based approach to meaning. Participants were required to study lists of associated words and then to perform a recognition task with the mouse. Results showed that mouse trajectories were extensively affected by the semantic similarity between the words presented in the recognition phase and the ones previously studied. In particular, the higher the semantic similarity, the larger the conflict driving the choice and the higher the irregularity in the trajectory when correctly rejecting new words (i.e., the false memory items). Conversely, on the temporal evolution of the decision, our results showed that semantic similarity affects more complex temporal measures indexing the online decision processes subserving task performance. Together, these findings demonstrate that semantic similarity can affect human behavior at the level of motor control, testifying its influence on online decision-making processes. More generally, our findings complement previous seminal theories on false memory and provide insights into the impact of the semantic memory structure on different decision-making components.

Speech timing cues reveal deceptive speech in social deduction board games

The faculty of language allows humans to state falsehoods in their choice of words. However, while what is said might easily uphold a lie, how it is said may reveal deception. Hence, some features of the voice that are difficult for liars to control may keep speech mostly, if not always, honest. Previous research has identified that speech timing and voice pitch cues can predict the truthfulness of speech, but this evidence has come primarily from laboratory experiments, which sacrifice ecological validity for experimental control. We obtained ecologically valid recordings of deceptive speech while observing natural utterances from players of a popular social deduction board game, in which players are assigned roles that either induce honest or dishonest interactions. When speakers chose to lie, they were prone to longer and more frequent pauses in their speech. This finding is in line with theoretical predictions that lying is more cognitively demanding. However, lying was not reliably associated with vocal pitch. This contradicts predictions that increased physiological arousal from lying might increase muscular tension in the larynx, but is consistent with human specialisations that grant Homo sapiens sapiens an unusual degree of control over the voice relative to other primates. The present study demonstrates the utility of social deduction board games as a means of making naturalistic observations of human behaviour from semi-structured social interactions.

Assessing Deception in Questionnaire Surveys With Eye-Tracking

Deceit often occurs in questionnaire surveys, which leads to the misreporting of data and poor reliability. The purpose of this study is to explore whether eye-tracking could contribute to the detection of deception in questionnaire surveys, and whether the eye behaviors that appeared in instructed lying still exist in spontaneous lying. Two studies were conducted to explore eye movement behaviors in instructed and spontaneous lying conditions. The results showed that pupil size and fixation behaviors are both reliable indicators to detect lies in questionnaire surveys. Blink and saccade behaviors do not seem to predict deception. Deception resulted in increased pupil size, fixation count and duration. Meanwhile, respondents focused on different areas of the questionnaire when lying versus telling the truth. Furthermore, in the actual deception situation, the linear support vector machine (SVM) deception classifier achieved an accuracy of 74.09%. In sum, this study indicates the eye-tracking signatures of lying are not restricted to instructed deception, demonstrates the potential of using eye-tracking to detect deception in questionnaire surveys, and contributes to the questionnaire surveys of sensitive issues.

Nothing but the truth? Effects of faking on the validity of the crosswise model

In self-reports, socially desirable responding threatens the validity of prevalence estimates for sensitive personal attitudes and behaviors. Indirect questioning techniques such as the crosswise model attempt to control for the influence of social desirability bias. The crosswise model has repeatedly been found to provide more valid prevalence estimates than direct questions. We investigated whether crosswise model estimates are also less susceptible to deliberate faking than direct questions. To this end, we investigated the effect of "fake good" instructions on responses to direct and crosswise model questions. In a sample of 1,946 university students, 12-month prevalence estimates for a sensitive road traffic behavior were higher and thus presumably more valid in the crosswise model than in a direct question. Moreover, "fake good" instructions severely impaired the validity of the direct questioning estimates, whereas the crosswise model estimates were unaffected by deliberate faking. Participants also reported higher levels of perceived confidentiality and a lower perceived ease of faking in the crosswise model compared to direct questions. Our results corroborate previous studies finding the crosswise model to be an effective tool for counteracting the detrimental effects of positive self-presentation in surveys on sensitive issues.

Mouse-tracking reveals cognitive conflict during negative impression formation in women with Borderline Personality Disorder or Social Anxiety Disorder

Individuals with Borderline Personality Disorder (BPD) or Social Anxiety Disorder (SAD) suffer from substantial interpersonal dysfunction and have difficulties establishing social bonds. A tendency to form negative first impressions of others could contribute to this by way of reducing approach behavior. We tested whether women with BPD or SAD would show negative impression formation compared to healthy women (HCs). We employed the Thin Slices paradigm and showed videos of 52 authentic target participants to 32 women with BPD, 29 women with SAD, and 37 HCs. We asked participants to evaluate whether different positive or negative adjectives described targets and expected BPD raters to provide the most negative ratings, followed by SAD and HC. BPD and SAD raters both agreed with negative adjectives more often than HCs (e.g., ‘Yes, the person is greedy’), and BPD raters rejected positive adjectives more often (e.g., ‘No, the person is not humble.’). However, BPD and SAD raters did not differ significantly from each other. Additionally, we used the novel process tracing method mouse-tracking to assess the cognitive conflict (via trajectory deviations) raters experienced during decision-making. We hypothesized that HCs would experience more conflict when making unfavorable (versus favorable) evaluations and that this pattern would flip in BPD and SAD. We quantified cognitive conflict via maximum absolute deviations (MADs) of the mouse-trajectories. As hypothesized, HCs showed more conflict when rejecting versus agreeing with positive adjectives. The pattern did not flip in BPD and SAD but was substantially reduced, such that BPD and SAD showed similar levels of conflict when rejecting and agreeing with positive adjectives. Contrary to the hypothesis for BPD and SAD, all three groups experienced substantial conflict when agreeing with negative adjectives. We discuss therapeutic implications of the combined choice and mouse-tracking results.

Detecting faking-good response style in personality questionnaires with four choice alternatives

Deliberate attempts to portray oneself in an unrealistic manner are commonly encountered in the administration of personality questionnaires. The main aim of the present study was to explore whether mouse tracking temporal indicators and machine learning models could improve the detection of subjects implementing a faking-good response style when answering personality inventories with four choice alternatives, with and without time pressure. A total of 120 volunteers were randomly assigned to one of four experimental groups and asked to respond to the Virtuous Responding (VR) validity scale of the PPI-R and the Positive Impression Management (PIM) validity scale of the PAI via a computer mouse. A mixed design was implemented, and predictive models were calculated. The results showed that, on the PIM scale, faking-good participants were significantly slower in responding than honest respondents. Relative to VR items, PIM items are shorter in length and feature no negations. Accordingly, the PIM scale was found to be more sensitive in distinguishing between honest and faking-good respondents, demonstrating high classification accuracy (80–83%).

Interrogative suggestibility in the elderly

Interrogative suggestibility (IS) describes the extent to which an individual behavioral response is affected by messages communicated during formal questioning within a closed social interaction. The present study aimed at improving knowledge about IS in the elderly (aged 65 years and older), in particular about its association with both emotive/affective and cognitive variables. The sample (N = 172) was divided into three groups on the basis of age: late adult (aged 55-64, N = 59), young elderly (aged 65-74, N = 63), and elderly (aged 75 and older, N = 50). Cognitive (i.e., Kaufman Brief Intelligence Test-2, Rey Auditory Verbal Learning Test), emotive/affective (i.e., Rosenberg Self-Esteem Scale, Marlowe-Crowne Social Desirability Scale, Penn State Worry Questionnaire) and suggestibility measures (i.e., Gudjonsson Suggestibility Scale-2) were administered. In order to identify differences and associations between groups in IS, cognitive and emotive/affective variables, ANOVAs tests and Pearson's correlations were run. Furthermore, moderation analyses and hierarchical regression were set to determine whether age, cognitive and emotive/affective variables predicted IS components (i.e., Yield and Shift). Finally, machine learning models were developed to highlight the best strategy for classifying elderly subjects with high suggestibility. The results corroborated the significant link between IS and age, showing that elderly participants had the worst performance on all suggestibility indexes. Age was also the most important predictor of both Yield and Shift. Results also confirmed the important role of non-verbal intelligence and memory impairment in explaining IS dimensions, showing that these associations were stronger in young elderly and elderly groups. Implications about interrogative procedures with older adults were discussed.

The Development of a Short Version of the SIMS Using Machine Learning to Detect Feigning in Forensic Assessment

In the present study, we applied machine learning techniques to evaluate whether the Structured Inventory of Malingered Symptomatology (SIMS) can be reduced in length yet maintain accurate discrimination between consistent participants (i.e., presumed truth tellers) and symptom producers. We applied machine learning item selection techniques on data from Mazza et al. (2019c) to identify the minimum number of original SIMS items that could accurately distinguish between consistent participants, symptom accentuators, and symptom producers in real personal injury cases. Subjects were personal injury claimants who had undergone forensic assessment, which is known to incentivize malingering and symptom accentuation. Item selection yielded short versions of the scale with as few as 8 items (to differentiate between consistent participants and symptom producers) and as many as 10 items (to differentiate between consistent and inconsistent participants). The scales had higher classification accuracy than the original SIMS and did not show the bias that was originally reported between false positives and false negatives.

How to Improve Compliance with Protective Health Measures during the COVID-19 Outbreak: Testing a Moderated Mediation Model and Machine Learning Algorithms

In the wake of the sudden spread of COVID-19, a large amount of the Italian population practiced incongruous behaviors with the protective health measures. The present study aimed at examining psychological and psychosocial variables that could predict behavioral compliance. An online survey was administered from 18-22 March 2020 to 2766 participants. Paired sample t-tests were run to compare efficacy perception with behavioral compliance. Mediation and moderated mediation models were constructed to explore the association between perceived efficacy and compliance, mediated by self-efficacy and moderated by risk perception and civic attitudes. Machine learning algorithms were trained to predict which individuals would be more likely to comply with protective measures. Results indicated significantly lower scores in behavioral compliance than efficacy perception. Risk perception and civic attitudes as moderators rendered the mediating effect of self-efficacy insignificant. Perceived efficacy on the adoption of recommended behaviors varied in accordance with risk perception and civic engagement. The 14 collected variables, entered as predictors in machine learning models, produced an ROC area in the range of 0.82-0.91 classifying individuals as high versus low compliance. Overall, these findings could be helpful in guiding age-tailored information/advertising campaigns in countries affected by COVID-19 and directing further research on behavioral compliance.