Skip to Content
  • Proceeding Paper
  • Open Access

9 November 2026

A Results-Based Evaluation Framework for Smart Learning Environments: Use Cases, User Testing, and Validation Design of the OSEME Platform †

,
,
,
and
1
Department of Informatics, Ionian University, Plateia Tsirigoti 7, 49100 Corfu, Greece
2
Institute of Computer Science, Vilnius University, LT-08303 Vilnius, Lithuania
*
Author to whom correspondence should be addressed.
†
Presented at the 2nd International Conference on Engineering, Technology, and Applied Science Innovations (ICETASI 2026), Zakynthos, Greece, 24–26 September 2026.
Eng. Proc.2026, 167(1), 20;https://doi.org/10.3390/engproc2026167020 
(registering DOI)

Abstract

Smart learning environments (SLEs) extend conventional Learning Management Systems by adapting content delivery to the cognitive profile, prior knowledge, and behavioral patterns of individual learners. Although the technical realization of such systems is increasingly well documented, their empirical evaluation remains comparatively underdeveloped, and assessment efforts frequently rely on subjective impressions rather than reproducible measurement. This paper addresses that gap by proposing a results-based, tri-pivotal evaluation framework that unifies pedagogical, technological-usability, and learning analytics dimensions into a single, database-grounded measurement model. The framework is instantiated on OSEME, an ontology-driven adaptive platform that integrates a Felder–Silverman learning style profiler, a domain-knowledge assessment in Music History, and real-time analytics visualization within a modular PHP/MySQL architecture. To operationalize the framework, we specify formal use cases, a structured user testing protocol with task-level success criteria, and a set of case-study designs, including a controlled A/B retention experiment and a System Usability Scale (SUS) assessment. Use cases, user tests, and case studies are presented in tabular form to support replication. The contribution is methodological: a transferable evaluation blueprint that converts platform telemetry into actionable evidence of pedagogical effectiveness, technical performance, and usability.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.