Using artificial intelligence to assess personal qualities in college admissions.

Personal qualities like prosocial purpose and leadership predict important life outcomes, including college success. Unfortunately, the holistic assessment of personal qualities in college admissions is opaque and resource intensive. Can artificial intelligence (AI) advance the goals of holistic admissions? While cost-effective, AI has been criticized as a "black box" that may inadvertently penalize already disadvantaged subgroups when used in high-stakes settings. Here, we consider an AI approach to assessing personal qualities that aims to overcome these limitations. Research assistants and admissions officers first identified the presence/absence of seven personal qualities in n = 3131 applicant essays describing extracurricular and work experiences. Next, we fine-tuned pretrained language models with these ratings, which successfully reproduced human codes across demographic subgroups. Last, in a national sample (N = 309,594), computer-generated scores collectively demonstrated incremental validity for predicting 6-year college graduation. We discuss challenges and opportunities of AI for assessing personal qualities.

How Does High School Extracurricular Participation Predict Bachelor's Degree Attainment? It is Complicated.

This study answered novel questions about the connection between high school extracurricular dosage (number of activities and participation duration) and the attainment of a bachelor's degree. Using data from the Common Application and the National Student Clearinghouse (N = 311,308), we found that greater extracurricular participation positively predicted bachelor's degree attainment. However, among students who ultimately earned a bachelor's degree, participating in more than a moderate number of high school activities (3 or 4) predicted decreasing odds of earning a bachelor's degree on time (within 4 years). This effect intensified as participation duration increased, such that students who participated in the greatest number of high school activities for the most years were the most likely to delay college graduation.

Low-income mothers' entry into postsecondary education during middle childhood: Effects on adolescents.

This study tests whether young adolescents' achievement and behavior are associated with their mother's entry into post-secondary education (PSE) during their middle childhood years. It also examines five family processes that may link maternal PSE to development in middle childhood (income, home learning environment, mother's educational expectations for child, maternal presence, and family affective climate). The sample selects low-income families from the National Longitudinal Survey of Youth of 1979. Propensity score weighting adjusts for mothers' self-selection into PSE. We find that adolescents whose mothers entered PSE in their middle childhood scored higher than their peers on math, but similarly on reading, behavior problems, delinquency, and substance use. There were no associations between mothers' PSE entry and the proposed mediators.

Collective efficacy and the contingent consequences of exposure to life-threatening violence.

Neighborhood research has increasingly emphasized the potential for contextual characteristics to moderate the effects of youths' experiences on their outcomes. Drawing on collective efficacy theory, we examine the variable consequences of youths' exposures to life-threatening violence across neighborhoods. We argue that strong community normative orientations supporting the control of violence diminish the negative effect of exposure to severe violence on subsequent mental health among urban youth. We also consider the extent to which the consequences of exposure to violence vary by gender. Employing data from the Project on Human Development in Chicago Neighborhoods, we estimate a series of multivariate, multilevel linear models of internalizing and externalizing symptoms. Results indicate that, for girls, exposure to life-threatening violence (witnessing someone being attacked with a weapon or shot) increases both internalizing and externalizing symptoms. However, this effect achieves statistical significance only for girls who reside in neighborhoods with lower collective efficacy. For boys, our analyses offered weaker evidence of violence exposure effects on mental health. Implications for research on the social context of mental health are discussed.

"Feeling disorder" as a comparative and contingent process: gender, neighborhood conditions, and adolescent mental health.

We explore the effects of neighborhood social disorder on internalizing symptoms among urban youth by focusing on three questions. First, we ask whether the impact of social disorder on internalizing symptoms results from comparisons with conditions measured locally or across the entire city. Second, we consider whether neighborhood collective efficacy modifies disorder's effect on internalizing symptoms. Finally, we assess whether these effects vary by gender. Analyses of survey data on 2,367 youth from the Project on Human Development in Chicago Neighborhoods indicate that social disorder is positively associated with girls' internalizing symptoms when measured as a deviation from a neighborhood cluster (NC--two to three census tracts) mean. High collective efficacy within girls' NCs attenuates disorder effects on their internalizing symptoms. We find no evidence of disorder or collective efficacy effects on boys' internalizing symptoms.

Context matters: links between neighborhood discrimination, neighborhood cohesion and African American adolescents' adjustment.

Racial discrimination has serious negative consequences for the adjustment of African American adolescents. Taking an ecological approach, this study examined the linkages between perceived racial discrimination within and outside of the neighborhood and urban adolescents' externalizing and internalizing behaviors, and tested whether neighborhood cohesion operated as a protective factor. Data came from 461 African American adolescents (mean age = 15.24 years, SD = 1.56; 50 % female) participating in the Project on Human Development in Chicago Neighborhoods. Multilevel models revealed that perceived discrimination within youth's neighborhoods was positively related to externalizing, and discrimination both within and outside of youth's neighborhoods predicted greater internalizing problems. Neighborhood cohesion moderated the association between within-neighborhood discrimination and externalizing. Specifically, high neighborhood cohesion attenuated the association between within-neighborhood discrimination and externalizing. The discussion centers on the implications of proximal stressors and neighborhood cohesion for African American adolescents' adjustment.

Can Organized Youth Activities Protect Against Internalizing Problems Among Adolescents Living in Violent Homes?

Using longitudinal data from a subsample of Hispanic, African American, and white youth enrolled in the Project on Human Development in Chicago Neighborhoods (N = 1,419), we examined the effects of both parental involvement in domestic violence and youth participation in organized out-of-school-time activities on internalizing symptoms during adolescence. We also examined the extent to which participation in organized activities protected youth against the internalizing consequences of domestic violence. We found that intensive participation in either afterschool programs or extracurricular activities was inversely associated with youth internalizing problems. Moreover, we found that intensive participation in afterschool programs weakened the association between parents' domestic violence and youths' internalizing problems.

The Mediated and Moderated Effects of Family Support on Child Maltreatment.

Previous research has linked parents' social support to decreased child maltreatment but questions remain surrounding the mechanisms explaining this association. Further, it is unclear whether this association applies to support provided by family alone (and not friends), and whether it is moderated by the presence of neighborhood violence. Based on a sample of parents of children aged 3-15 in Chicago, we find that parents' family support is associated with a lower risk of child maltreatment. This association is partly mediated by reduced parental depression, but only in neighborhoods with average or high levels of violence. In neighborhoods with low levels of violence, the inverse association between family support and maltreatment is equally strong, but it is not mediated by reduced depression.

Exploring the Link between Caregiver Affect and Adolescent Sexual Behavior: Does Neighborhood Disadvantage Matter?

In a sample of urban youth (N = 1,070), we examined the links between primary caregiver affect (i.e., warmth and hostility) and two measures of sexual behavior in adolescence - early sexual initiation and sex with multiple partners. We also examined the extent to which neighborhood disadvantage moderated associations between caregiver affect and adolescent sexual behavior. We found that caregiver hostility was positively associated with early sex and sex with multiple partners in neighborhoods characterized by high levels of disadvantage, but inversely associated with both sex outcomes in neighborhoods characterized by low levels of disadvantage. Caregiver warmth, on the other hand, was inversely associated with early sexual initiation and sex with multiple partners in all neighborhoods regardless of neighborhood disadvantage.

Sports participation and juvenile delinquency: the role of the peer context among adolescent boys and girls with varied histories of problem behavior.

In a study of 1,344 urban adolescents, the authors examined the relation between participation in organized sports and juvenile delinquency. They compared youth who participated in sports to those who only participated in nonathletic activities and to those who did not participate in any organized activities. They also examined the indirect relations between sports and delinquency via 2 peer-related constructs-deviant peer affiliations and unstructured socializing. Finally, they examined the extent to which gender and prior externalizing problems moderated the direct and indirect relations between sports participation and delinquency. The authors found that the odds of nonviolent delinquency were higher among boys who participated in sports when compared to boys who participated only in nonathletic activities but not when compared to boys who did not participate in any organized activities. Deviant peer affiliations and unstructured socializing mediated the relation between sports participation and boys' nonviolent delinquency. Moreover, prior externalizing problems moderated the mediated path through peer deviance. The authors did not, however, find direct, mediated, or moderated relations between sports and boys' violent delinquency nor between sports and girls' violent or nonviolent delinquency.

ADOLESCENTS' EXPOSURE TO COMMUNITY VIOLENCE: ARE NEIGHBORHOOD YOUTH ORGANIZATIONS PROTECTIVE?

Using data from the Project on Human Development in Chicago Neighborhoods (PHDCN), we identified a significant inverse association between the variety of youth organizations available at the neighborhood level and adolescents' exposure to community violence. We examined two non-competing explanations for this finding. First, at the individual level, we tested the hypothesis that access to a greater variety of neighborhood youth organizations predicts adolescents' participation in organized community-based activities, which, in turn, protects against community violence exposure. Second, at the neighborhood level, we tested the hypothesis that lower violent crime rates explain the inverse relation between neighborhood youth organization variety and community violence exposure. Our findings supported the latter of these two mechanisms.

Adolescents' participation in organized activities and developmental success 2 and 8 years after high school: do sponsorship, duration, and intensity matter?

Using data from the National Education Longitudinal Study, the authors examined relations between educational, civic, and occupational success in young adulthood and the duration and intensity of participation in organized activities during high school. They also examined these relations as a function of sponsorship (i.e., school- vs. community-sponsored organized activities). They found that youths who participated in organized activities for 2 years demonstrated more favorable educational and civic outcomes in young adulthood than those who participated for 1 year. More intensive participation was also associated with greater educational, civic, and occupational success in young adulthood--particularly among youths who participated in activities for 2 years. Educational attainment often mediated the relations between temporal measures of participation and young adult civic and occupational outcomes. With the exception of analyses examining occupational success, findings varied little as a function of sponsorship. Of note, analyses revealed that both temporal measures of participation were positively associated with young adult outcomes as many as 8 years after high school.

Peer influence on risk taking, risk preference, and risky decision making in adolescence and adulthood: an experimental study.

In this study, 306 individuals in 3 age groups--adolescents (13-16), youths (18-22), and adults (24 and older)--completed 2 questionnaire measures assessing risk preference and risky decision making, and 1 behavioral task measuring risk taking. Participants in each age group were randomly assigned to complete the measures either alone or with 2 same-aged peers. Analyses indicated that (a) risk taking and risky decision making decreased with age; (b) participants took more risks, focused more on the benefits than the costs of risky behavior, and made riskier decisions when in peer groups than alone; and (c) peer effects on risk taking and risky decision making were stronger among adolescents and youths than adults. These findings support the idea that adolescents are more inclined toward risky behavior and risky decision making than are adults and that peer influence plays an important role in explaining risky behavior during adolescence.