OUR PROJECTS

LATEST FINDINGS

The Use of Machine Learning to Predict Offline Adolescent e-Cigarette Use: A Proof-of-Concept 

Identification of adolescent e-cigarette use could inform prevention and intervention programming and reduce associated consequences. One way to predict those engaging in use is by examining social media profiles and metrics. Most studies examining substance use content on social media employ self-report or human coding that have methodological limitations. Thus, the current study developed a supervised machine learning algorithm to classify participants into e-cigarette use categories based on Instagram metrics. The final model accurately detected e-cigarette use 71% of the time. Findings indicate that supervised learning can predict adolescent e-cigarette use with accuracy consistent with other clinical populations. This study establishes that universal aspects of social media may be harbingers for policy makers and tech companies to provide targeted support and messaging.

Beyond the Family: Peer and Neighborhood Contexts Buffer the Effects of Childhood Threat and Deprivation on Adolescent Functioning

Little research has examined whether adaptive socialization contexts outside the family buffer distinct adversity dimensions reflecting the threat-deprivation framework, particularly in relation to the understudied construct of sexual body-esteem. Grounded in the threat and deprivation framework, we examined whether positive peer involvement and neighborhood social cohesion buffer the impact of childhood threat and deprivation on internalizing and externalizing problems and sexual body-esteem. Findings highlight the role of protective factors in mitigating the impact of childhood adversity of adolescent functioning.

Emotion Dysregulation and Dissociation Mediate the Association between Alexithymia and Depressive Symptoms in Individuals with Alcohol Use Disorder 

Dissociation may be considered both a severe psychopathological symptom and an everyday life experience. Still, little is known about the role of dissociation in  emotion processing of individuals with alcohol use disorder (AUD), as the results of current studies remain inconclusive. The aim of this study was to examine associations between dissociation, emotional processing (emotion dysregulation; alexithymia) and depressive symptoms in patients with AUD and healthy individuals. Associations between emotion processing characteristics, dissociation, and depressive symptom severity differ in individuals with and without AUD. These results suggest that dissociation might be a promising target for therapeutic interventions among individuals with AUD.