Exploratory Machine Learning Modeling of Adaptive and Maladaptive Personality Traits from Passively Sensed Behavior.
Ontology highlight
ABSTRACT:
SUBMITTER: Yan R
PROVIDER: S-EPMC8951872 | biostudies-literature | 2022 Jul
REPOSITORIES: biostudies-literature
Publications
Exploratory Machine Learning Modeling of Adaptive and Maladaptive Personality Traits from Passively Sensed Behavior.
Yan Runze R Ringwald Whitney R WR Hernandez Julio Vega JV Kehl Madeline M Bae Sang Won SW Dey Anind K AK Low Carissa C Wright Aidan G C AGC Doryab Afsaneh A
Future generations computer systems : FGCS 20220224
Continuous passive sensing of daily behavior from mobile devices has the potential to identify behavioral patterns associated with different aspects of human characteristics. This paper presents novel analytic approaches to extract and understand these behavioral patterns and their impact on predicting adaptive and maladaptive personality traits. Our machine learning analysis extends previous research by showing that both adaptive and maladaptive traits are associated with passively sensed behav ...[more]
Similar Datasets
Project description:BACKGROUND:Personality traits have been associated with a series of dysfunctional behaviors, ranging from violence to drug abuse and other risky behaviors. However, few studies have investigated motorcycle riders' personality traits, and no research using the psychobiological model of personality was found. Thus, we investigated the association between temperament and character traits and the occurrence of Motorcycle Accidents (MAs). METHODS:This cross-sectional study was conducted with a randomly selected of 153 Brazilian motorcycle riders (116 male and 37 female) with a mean age of 31.8randomly selected from the driver's license register, between 2015 and 2018. A sociodemographic questionnaire and the Temperament and Character Inventory (TCI) were used. RESULTS:Of the 153 participants, 146 (95.4%) reported having been involved in previous accidents, with the main causes as follows: "other drivers' careless behavior" (34.9%); "personal disrespect of traffic rules" (18.5%) and "personal careless behavior" (20.6%). Motorcyclists exhibited higher scores for the temperament factors of novelty seeking and persistence and lower scores for harm avoidance and reward dependence in comparison to the Brazilian population). Considering the reason for motorcycle use, the group of riders that used their motorcycles for work exhibited more temperament factors associated with risk behaviors than those who did not. It was observed that 68.9% of them had low Harm Avoidance (HA) factor scores, whereas 72.1% had high Novelty Seeking (NS) factor scores. DISCUSSION:The present study highlighted the influences of different personality traits on behaviors, decision-making and risk attitudes that can be potentially harmful to an individual and others. The results provided evidence that a lack of knowledge and experience in riding a motorcycle or any other vehicle, combined with personality traits, contribute to the adoption of risky behaviors that may act as triggers for most causes of Motorcycle Accidents.
| S-EPMC6894775 | biostudies-literature
Project description:BackgroundDimensional models of personality disorders postulate interpersonal dysfunction as the core feature of personality pathology, and describe maladaptive personality traits that characterize the specific pattern of dysfunction that is experienced. Herein, we examined whether maladaptive traits predict prosocial and trusting behavior, both of which are highly relevant behaviors for interpersonal functioning. Specifically, we examined antagonism as a predictor of prosocial behavior in a dictator game, and suspiciousness as a predictor of trust in the faith game.Materials and methodsThe study was preregistered and conducted online. The preregistration protocol is available at https://osf.io/er43j . Data and code are available at https://osf.io/2rvbg/ . Participants (N = 445) completed the German version of the Personality Inventory for DSM-5 to measure antagonism and suspiciousness. Additionally, they played the dictator game (more money taken away from another person indicates less prosocial behavior) and the faith game (choosing the sure choice instead of the faith choice indicates less trust). We conducted a linear regression model to test whether antagonism is associated with prosocial behavior in the dictator game and a logistic regression model to test whether suspiciousness predicts selection of the sure choice in the faith game.ResultsAs hypothesized, higher levels of antagonism were associated with less prosocial behavior in the dictator game. The remaining hypotheses were not supported, as suspiciousness was not significantly associated with the likelihood of choosing the sure choice in the faith game. Exploratory analyses on participants' estimates of the sure choice amount suggest successful experimental manipulation in the faith game.ConclusionsThe results on antagonism and prosocial behavior are consistent with those of previous studies that used categorial classification systems of personality disorders or examined non-pathological personality traits. Potential explanations for the non-significant effects of suspiciousness are discussed, including the small size and range of the sure choice payoff and that the anonymity of the game may have precluded suspicious traits from expressing. Future research with higher stakes and known interaction partners is needed to further probe the effects of suspiciousness.
| S-EPMC9648038 | biostudies-literature
Project description:The aim of this study was to evaluate the predictive value of the constructs proposed by two influential theoretical frameworks: the Protection Motivation Theory (PMT) and the Big Five (B5) model of personality in predicting health-related coping behavior during the SARS-CoV-2 pandemic. Both adaptive (i.e., preventive) and maladaptive (i.e., avoidant behavior and wishful thinking) coping behavior was measured. The study was conducted during the first wave of the pandemic. The sample consisted of 397 persons from the general Polish population. The findings provided strong support for the PMT constructs' predictive value, especially with regard to pandemic-related adaptive behavior. The B5 personality traits accounted for a small proportion of the variability of coping behavior, especially when maladaptive behavior was the outcome. The PMT model showed incremental validity over and above demographic variables and personality traits in predicting preventive behavior, avoidant behavior, and wishful thinking; however, the patterns of relationships differ across the types of coping behavior. According to the current results, to increase adherence to preventive measures during an epidemic, all the PMT constructs should be considered while persuasive communication to the public is formulated.
| S-EPMC8525766 | biostudies-literature
Project description:BackgroundMental health disorders affect multiple aspects of patients' lives, including mood, cognition, and behavior. eHealth and mobile health (mHealth) technologies enable rich sets of information to be collected noninvasively, representing a promising opportunity to construct behavioral markers of mental health. Combining such data with self-reported information about psychological symptoms may provide a more comprehensive and contextualized view of a patient's mental state than questionnaire data alone. However, mobile sensed data are usually noisy and incomplete, with significant amounts of missing observations. Therefore, recognizing the clinical potential of mHealth tools depends critically on developing methods to cope with such data issues.ObjectiveThis study aims to present a machine learning-based approach for emotional state prediction that uses passively collected data from mobile phones and wearable devices and self-reported emotions. The proposed methods must cope with high-dimensional and heterogeneous time-series data with a large percentage of missing observations.MethodsPassively sensed behavior and self-reported emotional state data from a cohort of 943 individuals (outpatients recruited from community clinics) were available for analysis. All patients had at least 30 days' worth of naturally occurring behavior observations, including information about physical activity, geolocation, sleep, and smartphone app use. These regularly sampled but frequently missing and heterogeneous time series were analyzed with the following probabilistic latent variable models for data averaging and feature extraction: mixture model (MM) and hidden Markov model (HMM). The extracted features were then combined with a classifier to predict emotional state. A variety of classical machine learning methods and recurrent neural networks were compared. Finally, a personalized Bayesian model was proposed to improve performance by considering the individual differences in the data and applying a different classifier bias term for each patient.ResultsProbabilistic generative models proved to be good preprocessing and feature extractor tools for data with large percentages of missing observations. Models that took into account the posterior probabilities of the MM and HMM latent states outperformed those that did not by more than 20%, suggesting that the underlying behavioral patterns identified were meaningful for individuals' overall emotional state. The best performing generalized models achieved a 0.81 area under the curve of the receiver operating characteristic and 0.71 area under the precision-recall curve when predicting self-reported emotional valence from behavior in held-out test data. Moreover, the proposed personalized models demonstrated that accounting for individual differences through a simple hierarchical model can substantially improve emotional state prediction performance without relying on previous days' data.ConclusionsThese findings demonstrate the feasibility of designing machine learning models for predicting emotional states from mobile sensing data capable of dealing with heterogeneous data with large numbers of missing observations. Such models may represent valuable tools for clinicians to monitor patients' mood states.
| S-EPMC8088855 | biostudies-literature
Project description:ObjectiveSocial processing (SP) deficits manifest across numerous mental disorders. However, this research has been plagued by heterogeneity and a piecemeal approach whereby skills are examined in isolation rather than as part of an integrated cognitive system. Here, we combined two dimensional frameworks of psychopathology to address these limitations.MethodWe utilized the Alternative Model for Personality Disorders (AMPD) to distill trait-related heterogeneity within a community sample (n = 200), and the Research Domain Criteria (RDoC) 'Systems for Social Processes' to comprehensively assess SP. We first applied latent class analyses (LCA) to derive AMPD-based groups and subsequently contrasted the performance of these groups on a SP test battery that we developed to align with the RDoC SP constructs.ResultsOur LCA yielded four distinct subgroups. The recognizable trait profiles and psychopathological symptoms of these classes suggested they were clinically meaningful. The subgroups differed in their SP profiles: one displayed deficits regarding the self, a second displayed deficits in understanding others, a third displayed more severe deficits including affiliation problems, whilst the fourth showed normal performance.ConclusionsOur results support the link between clusters of maladaptive personality traits and distinctive profiles of SP deficits, which may inform research on disorders involving SP dysfunctions.
| S-EPMC9545362 | biostudies-literature
Project description:ObjectiveDuring the COVID-19 pandemic, people's behaviors have been considered an important factor in the spread of coronavirus. This situation led us to examine the role of personality in human behavior and its outcomes during the pandemic. This study examined the effect of normative, maladaptive, and dark personality traits on the probability of COVID-19 infection as mediated by psychological and behavioral responses to the pandemic.MethodsThe data was collected from 740 Iranians (mean age = 33.34) completing Big Five-10, Personality Inventory for DSM-5-Brief Form (PID-5-BF)-Adult, Short Dark Triad (SD3), Depression, Anxiety and Stress Scale - 21 Items (DASS-21), and Protective Behaviors inventories. We used structural equation modeling to fit a model from the personality traits to COVID-19 infection through mediating effects of psychological and behavioral responses using cross-sectional data.ResultsAll path models examined fit the data well. The normative traits openness, conscientiousness, neuroticism, introversion, and disagreeableness were positively related to social distancing. The pathological traits antagonism, detachment, negative affectivity, disinhibition, and psychoticism, and dark traits psychopathy, narcissism, and Machiavellianism were negatively associated with social distancing. Finally, social distancing was negatively related to infection rates and fully mediated all personality links with infection (β = -0.17, p < 0.001).ConclusionThe findings demonstrate that individual differences in personality predict behaviors crucial to pandemic mitigation. Social distancing can be, directly or indirectly, a significant underlying mechanism linking personality traits to the COVID-19 infection. Public health policymakers should consider personality-tailored interventions for maximizing preventive health behaviors and slowing the spread of infection. This knowledge also could contribute to more effective measures to prepare for public health emergencies in the future.
| S-EPMC11879987 | biostudies-literature
Project description:In a nationally representative sample from Poland (N = 755), we examined the relationships between the Dark Triad traits (i.e., psychopathy, Machiavellianism, and narcissism) and collective narcissism (i.e., agentic and communal) on the one hand, and behaviors related to the COVID-19 pandemic at (1) the zero-order level, at (2) the latent variance level, and (3) indirectly through health beliefs about the virus (i.e., the health belief model) on the other. We focused on preventive and hoarding behaviors as common reactions toward the pandemic. Participants characterized by the Dark Triad traits engaged less in prevention and more in hoarding, whereas those characterized by collective narcissism engaged in more hoarding only. Coronavirus-related health beliefs mediated patterns of prevention (fully) and hoarding (partially) in the latent Dark Triad (Dark Core) and collective narcissism. However, specific beliefs worked in opposite directions, resulting in a weak indirect effect for prevention and a null indirect effect for hoarding. The results point to the utility of health beliefs in predicting behaviors during the pandemic, explaining (at least in part) problematic behaviors associated with the dark personalities (i.e., Dark Triad, collective narcissism).
| S-EPMC7363424 | biostudies-literature
Project description:ObjectivesNon-adherence to medication is common in the adult ADHD clinical group. The goal of this pre-registered study was to examine whether the DSM-5 Alternative Model of Personality Disorder (AMPD), generality personality dysfunction (LPFS-BF 2.0) or maladaptive personality traits (PID-5), can predict time to premature discontinuation of pharmacological treatment beyond other known factors.MethodsA sample of 284 adult patients with ADHD (60.6% female; Mage = 32.31 years) were investigated for medication adherence from 2018 to 2023, using time-to-event analytic methods.ResultsOf the sample, 54 were found to have discontinued treatment prematurely without consulting their physician. Interestingly this group was prescribed considerably lower doses before discontinuation than adhering patients. General personality dysfunction and maladaptive antagonistic personality traits are implicated in varying degrees, with the specific maladaptive personality facets Intimacy Avoidance and Deceitfulness (PID-5) significantly predicting time to premature discontinuation of ADHD medication beyond other known reasons for non-adherence.ConclusionsThe broader implication is that the emerging personality pathology models hold promise to predict non-adherence in the adult ADHD population.
| S-EPMC11800730 | biostudies-literature
Project description:The aim of the current study was to investigate the intersecting roles of dysfunctional personality traits and coping styles in relation to psychological distress during the Italian national lockdown caused by the COVID-19 pandemic. Participants included 633 adults who completed questionnaires of maladaptive personality traits, coping styles, and psychological distress. Results indicated that all the maladaptive traits were associated with psychological distress with magnitude of associations strongest for Negative Affect and weakest for Antagonism. Maladaptive traits were also generally positively associated with avoidant/maladaptive and negatively associated with acceptance and positive reframing, forms of coping. A series of path analyses further demonstrated that coping strategies partially explained associations between maladaptive personality traits and psychological distress. All told, results suggest that during an unprecedented stressful time, associations between maladaptive personality traits and psychological distress may be, at least in part, explained by maladaptive coping strategies.
| S-EPMC8570824 | biostudies-literature
Project description:This paper reports a two-part study examining the relationship between fear of missing out (FoMO) and maladaptive behaviors in college students. This project used a cross-sectional study to examine whether college student FoMO predicts maladaptive behaviors across a range of domains (e.g., alcohol and drug use, academic misconduct, illegal behavior). Participants (N = 472) completed hard copy questionnaire packets assessing trait FoMO levels and questions pertaining to unethical and illegal behavior while in college. Part 1 utilized traditional statistical analyses (i.e., hierarchical regression modeling) to identify any relationships between FoMO, demographic variables (socioeconomic status, living situation, and gender) and the behavioral outcomes of interest. Part 2 looked to quantify the predictive power of FoMO, and demographic variables used in Part 1 through the convergent approach of supervised machine learning. Results from Part 1 indicate that college student FoMO is indeed related to many diverse maladaptive behaviors spanning the legal and illegal spectrum. Part 2, using various techniques such as recursive feature elimination (RFE) and principal component analysis (PCA) and models such as logistic regression, random forest, and Support Vector Machine (SVM), showcased the predictive power of implementing machine learning. Class membership for these behaviors (offender vs. non-offender) was predicted at rates well above baseline (e.g., 50% at baseline vs 87% accuracy for academic misconduct with just three input variables). This study demonstrated FoMO’s relationships with these behaviors as well as how machine learning can provide additional predictive insights that would not be possible through inferential statistical modeling approaches typically employed in psychology, and more broadly, the social sciences. Research in the social sciences stands to gain from regularly utilizing the more traditional statistical approaches in tandem with machine learning.
| S-EPMC9534387 | biostudies-literature