Modeling informal learning as a dynamic interaction process in digital learning environments
Bibliographic Data
| ID | 22167149 |
|---|---|
| Authors | William Villegas-Ch (0000-0002-5421-7710, Universidad de Las Américas), Pablo Palacios (Diego Portales University), Ángel Jaramillo-Alcázar (0000-0003-4143-2515, Universidad de Las Américas), Vanessa Guevara (Universidad Americana) |
| Year | 2026 |
| Volume | 11 |
| Publication date | 2026-05-07 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Frontiers in Education (JOURNAL) |
| Journal identifiers | ISSN: 2504-284X • E-ISSN: 2504-284X |
| Publisher | Frontiers Media SA (PUBLISHER • CH) |
| DOI | 10.3389/feduc.2026.1776945 |
| OpenAlex | W7160501974 |
| Language | EN |
| References cited | 12 |
Digital learning environments in higher education generate large volumes of interaction data that reflect a substantial portion of the learning processes occurring outside of formally assessed activities. However, these informal learning dynamics remain difficult to observe and analyze systematically due to their non-evaluative, irregular, and self-organized nature. Most current approaches to educational analytics focus on aggregate indicators or academic outcomes, limiting the understanding of interaction processes that emerge over time. This work proposes an empirical-computational framework for modeling informal learning by analyzing the temporal dynamics of non-evaluative digital interactions. It utilizes a hybrid data environment that integrates open datasets with calibrated and structurally coherent temporal interaction records. The analysis relies on dynamic engagement metrics that capture the intensity, variability, irregularity, and persistence of participation at the student-course level, without inferring individual cognitive states or assessing academic performance. The results show that informal interaction exhibits highly skewed distributions and high sparsity, with a mean daily intensity of approximately 1.95 events, standard deviations exceeding 3.0, and coefficients of variation with medians greater than 1, demonstrating that temporal irregularity is a structural property of the phenomenon. Comparative analysis across different data representations confirms the stability of these patterns despite differences in temporal resolution and aggregation level. At the same time, exploratory associations with global outcome variables show moderate, non-deterministic correlations. This study provides a reproducible, methodologically rigorous approach to analyzing informal learning as an emergent dynamic process in digital higher-education environments
Exploratory data analysis · Informal learning · Learning analytics · Educational Environments and Student Outcomes · Innovative Teaching and Learning Methods · Online Learning and Analytics
Artificial intelligence in personalized learning
Balancing’ privacy and open science in the context of Covid-19
Exploring Learners’ Perceptions of AI‐mediated informal digital Multilingual Learning
Understanding learners' perceptions of artificial intelligence-mediated Informal Digital Learning of English
| Citation velocity | historical |
|---|---|
| Highly cited | No |