The global SARS-CoV-2 outbreak and subsequent lockdown had a significant impact on people’s daily lives, with strong implications for stress levels due to the threat of contagion and restrictions to freedom. Given the link between high stress levels and adverse physical and mental consequences, the COVID-19 pandemic is certainly a global public health issue. In the present study, we assessed the effect of the pandemic on stress levels in N = 2053 Italian adults, and characterized more vulnerable individuals on the basis of sociodemographic features and stable psychological traits. A set of 18 psycho-social variables, generalized regressions, and predictive machine learning approaches were leveraged. We identified higher levels of perceived stress in the study sample relative to Italian normative values. Higher levels of distress were found in women, participants with lower income, and participants living with others. Higher rates of emotional stability and self-control, as well as a positive coping style and internal locus of control, emerged as protective factors. Predictive learning models identified participants with high perceived stress, with a sensitivity greater than 76%. The results suggest a characterization of people who are more vulnerable to experiencing high levels of stress during the COVID-19 pandemic. This characterization may contribute to early and targeted intervention strategies.

The spread of coronavirus disease 2019 (COVID-19) has called for unprecedented measures, including a national lockdown in Italy. The present study aimed at identifying psychological changes (e.g., changes in depression, stress, and anxiety levels) among the Italian public during the lockdown period, in addition to factors associated with these changes. An online follow-up survey was administered to 439 participants (original sample = 2766), between 28 April and 3 May 2020. A paired sample t-test tested for differences in stress, anxiety, and depression over the period. Multivariate regression models examined associations between sociodemographic variables, personality traits, coping strategies, depression, and stress. Results showed an increase in stress and depression over the lockdown, but not anxiety. Negative affect and detachment were associated with higher levels of depression and stress. Higher levels of depression at the start of the lockdown, as well as fewer coping strategies and childlessness, were associated with increased depression at follow-up, whereas higher levels of stress at the start of the lockdown and younger age were associated with higher stress at follow-up. These results may help us to identify persons at greater risk of suffering from psychological distress as a result lockdown conditions, and inform psychological interventions targeting post-traumatic symptoms.

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.

Recent controversies about the level of replicability of behavioral research analyzed using statistical inference have cast interest in developing more efficient techniques for analyzing the results of psychological experiments. Here we claim that complementing the analytical workflow of psychological experiments with Machine Learning-based analysis will both maximize accuracy and minimize replicability issues. As compared to statistical inference, ML analysis of experimental data is model agnostic and primarily focused on prediction rather than inference. We also highlight some potential pitfalls resulting from adoption of Machine Learning based experiment analysis. If not properly used it can lead to over-optimistic accuracy estimates similarly observed using statistical inference. Remedies to such pitfalls are also presented such and building model based on cross validation and the use of ensemble models. ML models are typically regarded as black boxes and we will discuss strategies aimed at rendering more transparent the predictions.

The detection of faked identities is a major problem in security. Current memory-detection techniques cannot be used as they require prior knowledge of the respondent’s true identity. Here, we report a novel technique for detecting faked identities based on the use of unexpected questions that may be used to check the respondent identity without any prior autobiographical information. While truth-tellers respond automatically to unexpected questions, liars have to “build” and verify their responses. This lack of automaticity is reflected in the mouse movements used to record the responses as well as in the number of errors. Responses to unexpected questions are compared to responses to expected and control questions (i.e., questions to which a liar also must respond truthfully). Parameters that encode mouse movement were analyzed using machine learning classifiers and the results indicate that the mouse trajectories and errors on unexpected questions efficiently distinguish liars from truth-tellers. Furthermore, we showed that liars may be identified also when they are responding truthfully. Unexpected questions combined with the analysis of mouse movement may efficiently spot participants with faked identities without the need for any prior information on the examinee.

The unexpected COVID-19 outbreak and subsequent lockdown impositions are having a significant impact on people’s day-to-day life, confronting Western countries with hitherto unknown contagion threats and restrictions on freedoms. Given the serious effects of stress on physical and mental health, the stressful impact of the COVID-19 emergency represents an important public health issue. The present study assessed the stressful impact of the COVID-19 epidemic in Italy, identifying possible mediators of perceived stress (sociodemographic variables and stable psychological traits). High levels of perceived stress were found in the Italian population. Being female, having low income and living with other people were associated with higher levels of stress. Higher rates of emotional stability, self-control, positive coping style and internal locus of control were protective factors against psychological distress. These results may provide indications for early and targeted prevention and intervention programs.

Background and Purpose. The use of machine learning (ML) models in the detection of malingering has yielded encouraging results, showing promising accuracy levels. We investigated the possible application of this methodology when trained on behavioral features, such as response time (RT) and time pressure, to identify faking behavior in self-report personality questionnaires. To do so, we reintroduced the article of Roma et al. (2018), which highlighted that RTs and time pressure are useful variables in the detection of faking; we then extended the number of participants and applied an ML analysis. Materials and Methods. The sample was composed of 175 subjects, of whom all were graduates (having completed at least 17 years of instruction), male, and Caucasian. Subjects were randomly assigned to four groups: honest speeded, faking-good speeded, honest unspeeded, and faking-good unspeeded. A software version of the Minnesota Multiphasic Personality Inventory-2 Restructured Form (MMPI-2-RF) was administered. Results. Results indicated that ML algorithms reached very high accuracies (around 95%) in detecting malingerers when subjects are instructed to respond under time pressure. The classifiers’ performance was lower when the subjects responded with no time restriction to the MMPI-2-RF items, with accuracies ranging from 75% to 85%. Further analysis demonstrated that T -scores of validity scales are ineffective to detect fakers when participants were not under temporal pressure (accuracies 55–65%), whereas temporal features resulted to be more useful (accuracies 70–75%). By contrast, temporal features and T -scores of validity scales are equally effective in detecting fakers when subjects are under time pressure (accuracies higher than 90%). Discussion. To conclude, results demonstrated that ML techniques are extremely valuable and reach high performance in detecting fakers in self-report personality questionnaires over more the traditional psychometric techniques. Validity scales MMPI-2-RF manual criteria are very poor in identifying under-reported profiles. Moreover, temporal measures are useful tools in distinguishing honest from dishonest responders, especially in a no time pressure condition. Indeed, time pressure brings out malingerers in clearer way than does no time pressure condition.

Identifying the true identity of a subject in the absence of external verification criteria (documents, DNA, fingerprints, etc.) is an unresolved issue. Here, we report an experiment on the verification of fake identities, identified by means of their specific keystroke dynamics as analysed in their written response using a computer keyboard. Results indicate that keystroke analysis can distinguish liars from truth tellers with a high degree of accuracy - around 95% - thanks to the use of unexpected questions that efficiently facilitate the emergence of deception clues.