Yigal Rosen (Harvard University) and Rob Rubin (Microsoft)
Personalized learning prioritizes a clear understanding of the needs and goals of each individual learner and tailoring of instruction and assessment to address those needs and goals. Ultimately, each learner’s progress toward clearly defined goals is continually assessed, the assessment occurs when a student is ready to demonstrate competency, and supporting materials are tailored to the needs of each learner. Despite the promising signs, there is a lack of evidence-based instructional design and supporting adaptive technology for effective personalized learning and experimentation to date. ALOSI is aimed to promote open source adaptive learning technology and evidence-based approaches for instructional design.
Harvard VPAL Research team partnered with Microsoft Learning Sciences team to develop ALOSI experimental adaptive framework. To utilize the framework, the team developed the Adaptive Engine, Bridge for Adaptivity LTI, and deployed the framework in a selected Microsoft course on edX “Essential Statistics for Data Analysis Using Excel”, with forthcoming deployments in HarvardX MOOCs, online learning at Harvard via Canvas LMS and more. To utilize the engine, the course team significantly enhanced the assessment scope, and included over 35 knowledge components and 400 assessment items tagged to those knowledge components. Learners were randomly assigned to three independent cohorts, two experimental and one non-adaptive group, so we can measure the effects of adaptive pathways on learning gains, persistence, time-to-mastery, and completion rates using different tuning parameters in the adaptive engine against a standard non-adaptive learning experience. In our next blog posts we will share insights on the development of the Adaptive Engine, Bridge for Adaptivity, instructional design, and preliminary findings from our pilot study.