This paper describes a nationwide learning analytics initiative in Uruguay focused on the future implementation of governmental policies to mitigate student retention and dropouts in secondary education. For this, data from a total of 258,440 students were used to generate automated models to predict students at risk of failure or dropping out. Data were collected from primary and secondary education from different sources and for the period between 2015 and 2020. Such data contains demographic information about the students and their trajectories from the first grade of primary school to the second grade of secondary school (e.g., student assessments in different subjects over the years, the amount of absences, participation in social welfare programs, and the zone of the school, among other factors). Predictive models using the random forest algorithm were trained, and their performances were evaluated with F1-Macro and AUROC measures. The models were planned to be applied in different periods of the school year for the regular secondary school and for the technical secondary school ((before the beginning of the school year and after the first evaluation meeting for each grade). A total of eight predictive models were developed considering this temporal approach, and after an analysis of bias considering three protected attributes (gender, school zone, and social welfare program participation), seven of them were approved to be used for prediction. The models achieved outstanding performances according to the literature, with an AUROC higher than 0.90 and F1-Macro higher than 0.88. This paper describes in depth the characteristics of the data gathered, the specifics of data preprocessing, and the methodology followed for model generation and bias analysis, together with the architecture developed for the deployment of the predictive models. Among other findings, the results of the paper corroborate the importance given in the literature of using the previous performances of the students in order to predict their future performances.

Developing communication skills in collaborative contexts is of special interest for educational institutions, since these skills are crucial to forming competent professionals for today’s world. New and accessible technologies open a way to analyze collaborative activities in face-to-face and non-face-to-face situations, where collaboration and student attitudes are difficult to measure using traditional methods. In this context, Multimodal Learning Analytics (MMLA) appear as an alternative to complement the evaluation and feedback of core skills. We present a MMLA platform to support collaboration assessment based on the capture and classification of non-verbal communication interactions. The developed platform integrates hardware and software, including machine learning techniques, to detect spoken interactions and body postures from video and audio recordings. The captured data is presented in a set of visualizations, designed to help teachers to obtain insights about the collaboration of a team. We performed a case study to explore if the visualizations were useful to represent different behavioral indicators of collaboration in different teamwork situations: a collaborative situation and a competitive situation. We discussed the results of the case study in a focus group with three teachers, to get insights in the usefulness of our proposal. The results show that the measurements and visualizations are helpful to understand differences in collaboration, confirming the feasibility the MMLA approach for assessing and providing collaboration insights based on non-verbal communication.

Today, we face academic, social, and economic losses associated with student dropouts. Several studies have applied data mining techniques to educational datasets to understand dropout profiles and recognize at-risk students. To identify the contextual (academic levels, modalities, and systems), technical (tasks, categories of algorithms, and tools), and data (types, coverage, and volume) characteristics related to these works, we performed a systematic literature review, considering institutional and academic degree dropout. Internationally recognized repositories were searched, and the selected articles demonstrated, among other characteristics, a greater exploration of educational, demographic, and economic data of undergraduate students from classification techniques of decision tree ensembles. In addition to not having identified any study from underdeveloped countries among the selected ones, we found shortcomings in the application of predictive models and in making their predictions available to academic managers, which suggests an underutilization of the efforts and potential of most of these studies in educational practice.

This study aims to capture evidence on the effectiveness of emergency remote learning mediated by educational technology according to the interaction levels of K-12 students. The study involved students from a public institution that adopted emergency remote learning during the COVID-19 pandemic. From a mixed approach that used quantitative and qualitative methods, data from 963 students were collected and analyzed on the domain and use of the virtual learning environment Redu. Data were collected through student interactions and classified according to eleven classes that were used to identify the level and characteristics of those interactions between students and educators. We also performed interviews with 13 students based on their interaction patterns (highly interact, sporadically interact, rarely interact) to characterize the students’ interaction strategies within the virtual learning environment and strategies without the use of the virtual learning environment. It was found that students seek other means to interact and to send requests for help, regularly interact about school content, participate in discussions, and contact peers and teachers. The results can serve as a basis for proposing new functionalities for virtual learning environments.