Early and Dynamic Socio-Academic Variables Related to Dropout Intention: A Predictive Model Made during the Pandemic

Predictive model of the dropout intention of Chilean university students

Dropping out of university studies is one of the current problems of Higher Education; the increased rates during the first year of the study programme is considerable around the world. Dropping out has negative social implications that are reflected at the personal, family, institutional, and educational levels. The aim of this study was to evaluate a predictive model considering the mediation of university social satisfaction and perceived academic performance within the relations between perceived social support, social self-efficacy and academic purposes with career satisfaction and dropout intention in Chilean university students. A non-experimental explanatory design of latent and observed variables was used. Structural equation analyses with Mplus software were performed. The sample consisted of 956 first year university students. The study complied with the ethical requirements for research with human subjects. As a result, a predictive model with adequate adjustment indexes was obtained. When evaluating the explanatory capacity through the coefficient of determination (R² ), it was observed that it explains 38.9 and 27.4% of the variance of the dropout intention and career satisfaction, respectively. This percentage of explanation indicates a large effect size in Social Sciences; therefore, they are considered adequate predictive models. The mediation of university social satisfaction on the relationships between social support, social self-efficacy, and academic purposes with academic adjustment and dropout intention was, respectively, confirmed. The perception of academic performance has less influence on dropout intention and on career satisfaction among first-year students. The model obtained allows explaining the dropout intention and career satisfaction in first year students. In addition, it is composed of variables that can potentially be modified in the interaction of students and professors.

Density-Based Unsupervised Learning Algorithm to Categorize College Students into Dropout Risk Levels

Compliance with the basic conditions of quality in higher education implies the design of strategies to reduce student dropout, and Information and Communication Technologies (ICT) in the educational field have allowed directing, reinforcing, and consolidating the process of professional academic training. We propose an academic and emotional tracking model that uses data mining and machine learning to group university students according to their level of dropout risk. We worked with 670 students from a Peruvian public university, applied 5 valid and reliable psychological assessment questionnaires to them using a chatbot-based system, and then classified them using 3 density-based unsupervised learning algorithms, DBSCAN, K-Means, and HDBSCAN. The results showed that HDBSCAN was the most robust option, obtaining better validity levels in two of the three internal indices evaluated, where the performance of the Silhouette index was 0.6823, the performance of the Davies–Bouldin index was 0.6563, and the performance of the Calinski–Harabasz index was 369.6459. The best number of clusters produced by the internal indices was five. For the validation of external indices, with answers from mental health professionals, we obtained a high level of precision in the F-measure: 90.9%, purity: 94.5%, V-measure: 86.9%, and ARI: 86.5%, and this indicates the robustness of the proposed model that allows us to categorize university students into five levels according to the risk of dropping out.