Fifteen Years of Learning Analytics Research: Topics, Trends, and Challenges
Valdemar Švábenský, Conrad Borchers, Elvin Fortuna, Elizabeth B. Cloude, Dragan Gašević
TL;DR
This paper analyzes 936 LAK papers published over 15 years (2011–2025) using unsupervised ML, NLP, and network analytics to map topic evolution, funding influences, and international collaboration. It identifies six enduring topical centers—self-regulated learning, dashboards and theory, social learning, automated feedback, multimodal analytics, and outcome prediction—and demonstrates systematic links between funders and topic centers, with increasing cross-country integration by 2024. The study also reveals stable topical centroids over time, but divergent trajectories across topics and countries, highlighting underrepresented contexts and suggesting governance and funding strategies to bridge centers and translate insights into practice. By providing a public dataset and code, the work offers a replicable living map of LAK’s development and guidance for future, practice-aligned research.
Abstract
The learning analytics (LA) community has recently reached two important milestones: celebrating the 15th LAK conference and updating the 2011 definition of LA to reflect the 15 years of changes in the discipline. However, despite LA's growth, little is known about how research topics, funding, and collaboration, as well as the relationships among them, have developed within the community over time. This study addressed this gap by analyzing all 936 full and short papers published at LAK over a 15-year period using unsupervised machine learning, natural language processing, and network analytics. The analysis revealed a stable core of prolific authors alongside high turnover of newcomers, systematic links between funding sources and research directions, and six enduring topical centers that remain globally shared but vary in prominence across countries. These six topical centers, which encompass LA research, are: self-regulated learning, dashboards and theory, social learning, automated feedback, multimodal analytics, and outcome prediction. Our findings highlight key challenges for the future: widening participation, reducing dependency on a narrow set of funders, and ensuring that emerging research trajectories remain responsive to educational practice and societal needs.