Figure 1 - uploaded by Learning Analytics
Content may be subject to copyright.
*Student*dashboard*for*Week*1* The!purpose!of!the!dashboard!is!to!encourage!the!students!to!finish!their!online!tasks.!The!effectiveness! of! a! learning! analytics! dashboard! is! examined! in! the! paper! by! (Lauría,! Moody,! Jayaprakash,! Jonnalagadda,!&!Baron,!2013).!This!article!gives!the!effect!of!the!use!of!a!soRcalled!Early!Warning!system! (EWS)!on!the!study!results.!An!EWS!is!used!to!identify!highRrisk!students!in!a!course!(Hu!et!al.,!2014)!as! early!as!possible!with!the!aim!of!changing!their!learning!behaviour.!The!students!in!courses!with!an!EWS! achieved!on!average!a!6%!higher!final!grade!than!the!control!group.!An!effect!of!the!system!is,!that!of! the!treatment!group!a!larger!group!withdrew!from!the!course:!25.6%,!compared!to!14.1%!of!the!control! group.!! The!Learning!Analytics!dashboard!(Figure!1)!was!implemented!on!a!weekly!basis.!The!dashboard! visualized!the!expected!result!and!risk!of!failure!for!the!student.!For!the!expected!result,!linear! regression!models!are!used,!and!for!the!risk!of!failure!decision!tree!algorithms!(Decision!Stump,! Adaboost)!(Hu!et!al.,!2014)!are!used.!These!models!were!created!through!WEKA!3.6!.!The!failure!risk! models!in!week!8!correctly!classified!88.8!%!of!the!instances!(607),!11.2%!of!the!instances!are!incorrectly! classified!(77).!The!expected!results!are!calculated!with!linear!regression!models!of!WEKA 3 .!In!week!8! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! !!!!!!!!!!!!!!!!!!!!!
Source publication
Practitioners spearhead a significant portion of learning analytics, relying on implementation and experimentation rather than on traditional academic research. The primary goal of the LAK practitioner track is to share thoughts and findings that stem from learning analytics project implementations. The proceedings of the practitioner track from LA...
Citations
Massive open online courses (MOOCs) represent important pedagogical transformations that aim at unlimited participation and open access to high-quality educational experiences and resources. MOOCs are quite different from classical distance learning settings in terms of their open-access features , such as open licensing of course content, and their use of specific infrastructures for communications and learning tools. Studies over the past 2 years (2018, 2019) have examined the multitude of experimental business models for MOOCs. However, MOOCs have also experimented with a wide variety of course content, teaching and learning methods, and assessment strategies. Very few articles have systematically examined these significant changes. To address this gap, we conducted an extensive, qualitative meta-analyses of over 200 peer-reviewed articles describing research on MOOCs. This analysis is organized around the following questions: (a) How can we classify existing MOOCs in terms of their support for learners and learning? (b) Which learners are benefiting from MOOCs, and to what degree have MOOCs explored approaches to student-centered learning? (c) To what degree are MOOCs meeting the needs of different learner audiences? (d) How can MOOC providers and participants communicate effectively to support student learning and engagement? (e) How can student activities be monitored to ensure that assessments of learning are performed effectively? The results of these analyses provide a reflection on the last decade of MOOC research and discussing the main achievements and the major research directions pursued in those years and points toward areas in need of additional research and development.
Learning analytics and visualizations make it possible to examine and communicate learners’ engagement, performance, and trajectories in online courses to evaluate and optimize course design for learners. This is particularly valuable for workforce training involving employees who need to acquire new knowledge in the most effective manner. This paper introduces a set of metrics and visualizations that aim to capture key dynamical aspects of learner engagement, performance, and course trajectories. The metrics are applied to identify prototypical behavior and learning pathways through and interactions with course content, activities, and assessments. The approach is exemplified and empirically validated using more than 30 million separate logged events that capture activities of 1,608 Boeing engineers taking the MITxPro Course, “Architecture of Complex Systems,” delivered in Fall 2016. Visualization results show course structure and patterns of learner interactions with course material, activities, and assessments. Tree visualizations are used to represent course hierarchical structures and explicit sequence of content modules. Learner trajectory networks represent pathways and interactions of individual learners through course modules, revealing patterns of learner engagement, content access strategies, and performance. Results provide evidence for instructors and course designers for evaluating the usage and effectiveness of course materials and intervention strategies.
