Hire me: Computational inference of hirability in employment interviews based on nonverbal behavior

Understanding the basis on which recruiters form hirability impressions for a job applicant is a key issue in organizational psychology and can be addressed as a social computing problem. We approach the problem from a face-to-face, nonverbal perspective where behavioral feature extraction and inference are automated. This paper presents a computational framework for the automatic prediction of hirability. To this end, we collected an audio-visual dataset of real job interviews where candidates were applying for a marketing job. We automatically extracted audio and visual behavioral cues related to both the applicant and the interviewer. We then evaluated several regression methods for the prediction of hirability scores and showed the feasibility of conducting such a task, with ridge regression explaining 36.2% of the variance. Feature groups were analyzed, and two main groups of behavioral cues were predictive of hirability: applicant audio features and interviewer visual cues, showing the predictive validity of cues related not only to the applicant, but also to the interviewer. As a last step, we analyzed the predictive validity of psychometric questionnaires often used in the personnel selection process, and found that these questionnaires were unable to predict hirability, suggesting that hirability impressions were formed based on the interaction during the interview rather than on questionnaire data.

Defining the Effect of the 16p11.2 Duplication on Cognition, Behavior, and Medical Comorbidities.

IMPORTANCE: The 16p11.2 BP4-BP5 duplication is the copy number variant most frequently associated with autism spectrum disorder (ASD), schizophrenia, and comorbidities such as decreased body mass index (BMI). OBJECTIVES: To characterize the effects of the 16p11.2 duplication on cognitive, behavioral, medical, and anthropometric traits and to understand the specificity of these effects by systematically comparing results in duplication carriers and reciprocal deletion carriers, who are also at risk for ASD. DESIGN, SETTING, AND PARTICIPANTS: This international cohort study of 1006 study participants compared 270 duplication carriers with their 102 intrafamilial control individuals, 390 reciprocal deletion carriers, and 244 deletion controls from European and North American cohorts. Data were collected from August 1, 2010, to May 31, 2015 and analyzed from January 1 to August 14, 2015. Linear mixed models were used to estimate the effect of the duplication and deletion on clinical traits by comparison with noncarrier relatives. MAIN OUTCOMES AND MEASURES: Findings on the Full-Scale IQ (FSIQ), Nonverbal IQ, and Verbal IQ; the presence of ASD or other DSM-IV diagnoses; BMI; head circumference; and medical data. RESULTS: Among the 1006 study participants, the duplication was associated with a mean FSIQ score that was lower by 26.3 points between proband carriers and noncarrier relatives and a lower mean FSIQ score (16.2-11.4 points) in nonproband carriers. The mean overall effect of the deletion was similar (-22.1 points; P < .001). However, broad variation in FSIQ was found, with a 19.4- and 2.0-fold increase in the proportion of FSIQ scores that were very low (≤40) and higher than the mean (>100) compared with the deletion group (P < .001). Parental FSIQ predicted part of this variation (approximately 36.0% in hereditary probands). Although the frequency of ASD was similar in deletion and duplication proband carriers (16.0% and 20.0%, respectively), the FSIQ was significantly lower (by 26.3 points) in the duplication probands with ASD. There also were lower head circumference and BMI measurements among duplication carriers, which is consistent with the findings of previous studies. CONCLUSIONS AND RELEVANCE: The mean effect of the duplication on cognition is similar to that of the reciprocal deletion, but the variance in the duplication is significantly higher, with severe and mild subgroups not observed with the deletion. These results suggest that additional genetic and familial factors contribute to this variability. Additional studies will be necessary to characterize the predictors of cognitive deficits.

Potential blindness in children of patients with hereditary bone disease.

Mono- and bi-allelic mutations in the low-density lipoprotein receptor related protein 5 (LRP5) may cause osteopetrosis, autosomal dominant and recessive exudative vitreoretinopathy, juvenile osteoporosis, or persistent hyperplastic primary vitreous (PHPV). We report on a child affected with PHPV and carrying compound mutations. The father carried the splice mutation and suffered from severe bone fragility since childhood. The mother carried the missense mutation without any clinical manifestations. The genetic diagnosis of their child allowed for appropriate treatment in the father and for the detection of osteopenia in the mother. Mono- and bi-allelic mutations in LRP5 may cause osteopetrosis, autosomal dominant and recessive exudative vitreoretinopathy, juvenile osteoporosis, or PHPV. PHPV is a component of persistent fetal vasculature of the eye, characterized by highly variable expressivity and resulting in a wide spectrum of anterior and/or posterior congenital developmental defects, which may lead to blindness. We evaluated a family diagnosed with PHPV in their only child. The child presented photophobia during the first 3 weeks of life, followed by leukocoria at 2 months of age. Molecular resequencing of NDP, FZD4, and LRP5 was performed in the child and segregation of the observed mutations in the parents. At presentation, fundus examination of the child showed a retrolental mass in the right eye. Ultrasonography revealed retinal detachment in both eyes. Thorough familial analysis revealed that the father suffered from many fractures since childhood without specific fragility bone diagnosis, treatment, or management. The mother was asymptomatic. Molecular analysis in the proband identified two mutations: a c.[2091+2T>C] splice mutation and c.[1682C>T] missense mutation. We report the case of a child affected with PHPV and carrying compound heterozygous LRP5 mutations. This genetic diagnosis allowed the clinical diagnosis of the bone problem to be made in the father, resulting in better management of the family. It also enabled preventive treatment to be prescribed for the mother and accurate genetic counseling to be provided.