Educational Technology and Computing

Educational technology and computing encompass the design, deployment and evaluation of digital tools, pedagogical strategies and data-driven processes to enhance learning, teaching and institutional performance. Core areas include adaptive learning systems that personalise content sequencing and feedback; learning analytics and educational data mining that extract insights from students’ digital footprints; online and blended modalities that extend instruction beyond traditional classrooms; and emergent fields such as artificial intelligence, virtual and augmented reality, and computational thinking in K–12 curricula. Together these developments promise to support differentiated instruction, evidence-based decision making and the cultivation of skills for a rapidly evolving digital society. Practical applications span from intelligent tutoring systems and MOOCs to programmable robotics in primary schools, reflecting broad interconnections across disciplines, contexts and learner profiles. The global significance of this research is manifest in efforts to promote educational equity, digital inclusion and lifelong learning amid accelerating technological change.

Research from Nature Portfolio

Researchers have proposed a behaviour classification-based e-learning performance (BCEP) prediction framework that fuses fine-grained online activity data into categorical feature sets, enhancing the accuracy of models forecasting student success in fully online learning. They further introduced a process-behaviour classification (PBC) model aligned with the stages of e-learning to better capture the temporal dynamics of learners’ interactions, demonstrating superior predictive validity on a large open-university dataset. In a separate study, a combined macro-level (demographic and prior-performance) and meso-level (app-based engagement and social-embeddedness) predictive model was applied to 50 000 undergraduates across four US institutions. Results showed that incorporating granular behavioural engagement metrics—such as network centrality within a campus communication app—enhanced dropout risk prediction (AUC up to 0.88), underscoring the added value of social experience data beyond conventional academic indicators.

Educational Technology and Computing publication trend

The graph below shows the total number of articles in educational technology and computing across all publications each year (not limited to Nature Index journals).

Technical terms

Adaptive Learning System: A digital environment that continuously assesses learner performance and preferences to dynamically modify content presentation, pacing and feedback in real time.

Learning Analytics: The measurement, collection and analysis of data about learners and their contexts to inform pedagogical strategies, identify at-risk students and optimise educational outcomes.

Educational Data Mining: The application of data-mining techniques—such as classification, clustering and association rule mining—to large educational datasets to uncover latent patterns and support decision making.

Predictive Modelling: The use of statistical or machine-learning algorithms to forecast future events—such as course completion or dropout risk—based on historical and behavioural data.

BCEP Prediction Framework: A behaviour classification-based e-learning performance model that fuses feature sets derived from different categories of online activity to enhance the accuracy of student success predictions.

Process-Behaviour Classification (PBC) Model: An e-learning behaviour classification approach aligned with stages of the learning process, designed to capture temporal correlations between actions and performance for improved prediction.

References

1. Predicting students’ performance in e-learning using learning process and behaviour data. Scientific Reports (2022).
2. Using machine learning to predict student retention from socio-demographic characteristics and app-based engagement metrics. Scientific Reports (2023).
3. Adaptive learning: toward an intentional model for learning process guidance based on learner’s motivation. Smart Learning Environments (2022).
4. i-Ntervene: applying an evidence-based learning analytics intervention to support computer programming instruction. Smart Learning Environments (2023).
5. AI-based adaptive personalized content presentation and exercises navigation for an effective and engaging E-learning platform. Multimedia Tools and Applications (2022).