Contemporary education is a vast field that is concerned with the performance of education systems. In a formal e-learning context, student dropout is considered one of the main problems and has received much attention from the learning analytics research community, which has reported several approaches to the development of models for the early prediction of at-risk students. However, maximizing the results obtained by predictions is a considerable challenge. In this work, we developed a solution using only students’ interactions with the virtual learning environment and its derivative features for early predict at-risk students in a Brazilian distance technical high school course that is 103 weeks in duration. To maximize results, we developed an elitist genetic algorithm based on Darwin’s theory of natural selection for hyperparameter tuning. With the application of the proposed technique, we predicted the student at risk with an Area Under the Receiver Operating Characteristic Curve (AUROC) above 0.75 in the initial weeks of a course. The results demonstrate the viability of applying interaction count and derivative features to generate prediction models in contexts where access to demographic data is restricted. The application of a genetic algorithm to the tuning of hyperparameters classifiers can increase their performance in comparison with other techniques.

Background: Mental health status assessment is mostly limited to clinical or research settings, but recent technological advances provide new opportunities for measurement using more ecological approaches. Leveraging apps already in use by individuals on their smartphones, such as chatbots, could be a useful approach to capture subjective reports of mood in the moment. Objective: This study aimed to describe the development and implementation of the Identifying Depression Early in Adolescence Chatbot (IDEABot), a WhatsApp-based tool designed for collecting intensive longitudinal data on adolescents’ mood. Methods: The IDEABot was developed to collect data from Brazilian adolescents via WhatsApp as part of the Identifying Depression Early in Adolescence Risk Stratified Cohort (IDEA-RiSCo) study. It supports the administration and collection of self-reported structured items or questionnaires and audio responses. The development explored WhatsApp’s default features, such as emojis and recorded audio messages, and focused on scripting relevant and acceptable conversations. The IDEABot supports 5 types of interactions: textual and audio questions, administration of a version of the Short Mood and Feelings Questionnaire, unprompted interactions, and a snooze function. Six adolescents (n=4, 67% male participants and n=2, 33% female participants) aged 16 to 18 years tested the initial version of the IDEABot and were engaged to codevelop the final version of the app. The IDEABot was subsequently used for data collection in the second- and third-year follow-ups of the IDEA-RiSCo study. Results: The adolescents assessed the initial version of the IDEABot as enjoyable and made suggestions for improvements that were subsequently implemented. The IDEABot’s final version follows a structured script with the choice of answer based on exact text matches throughout 15 days. The implementation of the IDEABot in 2 waves of the IDEA-RiSCo sample (140 and 132 eligible adolescents in the second- and third-year follow-ups, respectively) evidenced adequate engagement indicators, with good acceptance for using the tool (113/140, 80.7% and 122/132, 92.4% for second- and third-year follow-up use, respectively), low attrition (only 1/113, 0.9% and 1/122, 0.8%, respectively, failed to engage in the protocol after initial interaction), and high compliance in terms of the proportion of responses in relation to the total number of elicited prompts (12.8, SD 3.5; 91% out of 14 possible interactions and 10.57, SD 3.4; 76% out of 14 possible interactions, respectively). Conclusions: The IDEABot is a frugal app that leverages an existing app already in daily use by our target population. It follows a simple rule-based approach that can be easily tested and implemented in diverse settings and possibly diminishes the burden of intensive data collection for participants by repurposing WhatsApp. In this context, the IDEABot appears as an acceptable and potentially scalable tool for gathering momentary information that can enhance our understanding of mood fluctuations and development.

To present the protocol and methods for the prospective longitudinal assessments—including clinical and digital phenotyping approaches—of the Identifying Depression Early in Adolescence Risk Stratified Cohort (IDEA-RiSCo) study, which comprises Brazilian adolescents stratified at baseline by risk of developing depression or presence of depression. Of 7,720 screened adolescents aged 14 to 16 years, we recruited 150 participants (75 boys, 75 girls) based on a composite risk score: 50 with low risk for developing depression (LR), 50 with high risk for developing depression (HR), and 50 with an active untreated major depressive episode (MDD). Three annual follow-up assessments were conducted, involving clinical measures (parent- and adolescent-reported questionnaires and psychiatrist assessments), active and passive data sensing via smartphones, and neurobiological measures (neuroimaging and biological material samples). Retention rates were 96% (Wave 1), 94% (Wave 2), and 88% (Wave 3), with no significant differences by sex or group (p > .05). Participants highlighted their familiarity with the research team and assessment process as a motivator for sustained engagement. This protocol relied on novel aspects, such as the use of a WhatsApp bot, which is particularly pertinent for low- to-middle-income countries, and the collection of information from diverse sources in a longitudinal design, encompassing clinical data, self-reports, parental reports, Global Positioning System (GPS) data, and ecological momentary assessments. The study engaged adolescents over an extensive period and demonstrated the feasibility of conducting a prospective follow-up study with a risk-enriched cohort of adolescents in a middle-income country, integrating mobile technology with traditional methodologies to enhance longitudinal data collection.