Prediction of absenteeism in public schools teachers with machine learning

Social Vulnerability of Brazilian Metropolitan Schools and Teachers' Absence from Work Due to Vocal and Psychological Symptoms: A Multilevel Analysis

Teachers' voices and psychological symptoms are the main reasons for absence from work. The objectives of this study were: (i) to spatially represent, through a webGIS, the standardized rates of teachers' absences due to voice (outcome 1) and psychological symptoms (outcome 2) in each Brazilian Federative Unit (FU = 26 states plus Federal District) and (ii) to analyze the relationship between each national outcome rate and the Social Vulnerability Index (SVI) of the municipality where urban schools are located, adjusted for sex, age, and working conditions. This cross-sectional study comprised 4979 randomly sampled teachers working in basic education urban schools, of which 83.3% are women. The national absence rates were 17.25% for voice symptoms and 14.93% for psychological symptoms. The rates, SVI, and school locations in the 27 FUs are dynamically visualized in webGIS. The multilevel multivariate logistic regression model showed a positive association between voice outcome and high/very high SVI (OR = 1.05 [1.03; 1.07]), whereas psychological symptoms were negatively associated with high/very high SVI (OR = 0.86 [0.85 0.88]) and positively associated with intermediate SVI (OR = 1.15 [1.13; 1.16]), in contrast with low/very low SVI. Being a woman (voice: OR = 1.36 [1.35; 1.38]; psychological: 1.22 [1.21; 1.24]) and working in schools with various precarious conditions (17 variables) increased the odds of being absent due to voice and psychological symptoms. The results confirm the need for investments to improve working conditions in schools.

Deep learning-based school attendance prediction for autistic students

Autism Spectrum Disorder is a neurodevelopmental disorder characterized by deficits in social communication and interaction as well as the presence of repetitive, restricted patterns of behavior, interests, or activities. Many autistic students experience difficulty with daily functioning at school and home. Given these difficulties, regular school attendance is a primary source for autistic students to receive an appropriate range of needed educational and therapeutic interventions. Moreover, school absenteeism (SA) is associated with negative consequences such as school drop-out. Therefore, early SA prediction would help school districts to intervene properly to ameliorate this issue. Due to its heterogeneity, autistic students show within-group differences concerning their SA. A comprehensive statistical analysis performed by the authors shows that the individual and demographic characteristics of the targeted population are not predictive factors of SA. So, we used the students’ recent previous attendance to predict their future attendance. We introduce a deep learning-based framework for predicting short-and long-term SA of autistic students using the Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP) algorithms. The adopted algorithms outperform other machine learning algorithms. In detail, LSTM increased the accuracy and recall of short-term SA prediction by 20% and 13%, while the same scores of long-term SA prediction increased by 5% using MLP.