Copy the page URI to the clipboard
Kbaier, Dhouha and Mason, Andrew
(2024).
URL: https://thesis.psychologyresearch.co.uk/programme/
Abstract
In an era marked by rapid technological advancement, STEM education faces evolving challenges in fostering student success and engagement. The OELAssist project emerges as an initiative in online laboratories aimed at enhancing the student experience within the Open Engineering Lab (OEL) through innovative data-driven learning support mechanisms and advanced AI interventions.
With a focus on addressing the hurdles encountered during experimental activities, OELAssist aims to reduce attainment gaps, bolster student retention, and promote progression in OEL modules. Leveraging cutting-edge machine learning techniques and generative AI models, the project delves into real-time problem detection and personalised feedback provision, tailored to the unique needs of engineering students.
The project's structured framework encompasses two pivotal stages: identification and diagnosis, followed by intervention and remediation. Through meticulous data collection, analysis, and algorithm evaluation, OELAssist aims to discern patterns indicative of successful experiment completion. Subsequently, a robust feedback mechanism will be devised, enabled by generative AI models, to offer timely support and instructional resources to students navigating experimental challenges.
Aligned with the strategic objectives of The Open University, OELAssist not only contributes to enhancing student outcomes but also embodies a commitment to innovation in teaching and learning. The anticipated outcomes span beyond the institution, with dissemination efforts poised to share insights and best practices in STEM education across broader academic and professional communities.
To conclude, OELAssist has the potential to redefine the landscape of STEM education by synergising data analytics, AI-driven interventions, and student-centric approaches, within the context of online laboratories and distance education.
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)
