Massive open online course | EPFL Graph Search

A massive open online course (MOOC muːk) or an open online course is an online course aimed at unlimited participation and open access via the Web. In addition to traditional course materials, such as filmed lectures, readings, and problem sets, many MOOCs provide interactive courses with user forums or social media discussions to support community interactions among students, professors, and teaching assistants (TAs), as well as immediate feedback to quick quizzes and assignments. MOOCs are a widely researched development in distance education, first introduced in 2008, that emerged as a popular mode of learning in 2012, a year called the "Year of the MOOC". Early MOOCs (cMOOCs: Connectivist MOOCs) often emphasized open-access features, such as open licensing of content, structure and learning goals, to promote the reuse and remixing of resources. Some later MOOCs (xMOOCs: extended MOOCs) use closed licenses for their course materials while maint

Maintainable Online Classes

Alexandre David Koo

This project was initialized by Professor Prandoni from EPFL in the context of a bachelor project entitled "Maintainable Online Coursese". The motivations for this project was the lack of intuitive slideshow annotation software considering the current boom of online classes, most notably the MOOCs. One of the major limitations of current options are the fact that annotations and video tracks are interwoven, giving very little editing power after a recording has been done. Such editing could come in handy to correct mistakes or update a video lecture. In this application, we attempt to seperate out the two worlds of annotations and slide transitions(video) and experiement to see if such a setup could be beneficial to the workflow. In order to achieve this result, the approach has been to carefully and precisely register every slide transition and pen stroke timing, to then be able to succesfully replay the session but with full modularity when it comes to editing and modifications.

2016

Meta Transfer Learning for Early Success Prediction in MOOCs

Mirko Marras, Vinitra Swamy

Despite the increasing popularity of massive open online courses (MOOCs), many suffer from high dropout and low success rates. Early prediction of student success for targeted intervention is therefore essential to ensure no student is left behind in a course. There exists a large body of research in success prediction for MOOCs, focusing mainly on training models from scratch for individual courses. This setting is impractical in early success prediction as the performance of a student is only known at the end of the course. In this paper, we aim to create early success prediction models that can be transferred between MOOCs from different domains and topics. To do so, we present three novel strategies for transfer: 1) pre-training a model on a large set of diverse courses, 2) leveraging the pre-trained model by including meta information about courses, and 3) fine-tuning the model on previous course iterations. Our experiments on 26 MOOCs with over 145,000 combined enrollments and millions of interactions show that models combining interaction data and course information have comparable or better performance than models which have access to previous iterations of the course. With these models, we aim to effectively enable educators to warm-start their predictions for new and ongoing courses.

ACM2022

From Seminar to Lecture to MOOC: Scripting and Orchestration at Scale

Stian Haklev

This dissertation investigates the design of large online courses from the pedagogical perspective of knowledge communities. Much of the learning sciences literature has concerned itself with groups of up to 20-30 students, but in universities, courses of several hundred to more than a thousand students are common. At the same time, new models for life-long and informal learning, such as Massive Open Online Courses, are emerging. Amidst this growing enthusiasm for innovation around technology and design in teaching, there is a need for theoretically grounded innovations and rigorous research around practical models that support new approaches to learning. One recent model, known as Knowledge Community and Inquiry (KCI), engages students in the co-construction of a community knowledge base, with a commonly held understanding of the collective nature of their learning, and then provides a sequence of scaffolded inquiry activities where students make use of the knowledge base as a resource. Inspired by this approach to designing courses, the research began with a redesign of an in-service teacher education course, which increased in size from 25 to 75 students. This redesign was carefully analyzed, and design principles extracted. The second step was the design of a Massive Open Online Course for several thousand in-service teachers on technology and inquiry, in collaboration with an affiliated secondary school. A number of innovative design ideas were necessary to accommodate the large number of users, the much larger diversity in terms of background, interest, and engagement among MOOC learners, and the opportunities provided by the platform. The resulting design encompasses a 6- week long curriculum script, and a number of overlapping micro-scripts supported by a custom- written platform that integrated with the EdX platform in a seamless manner. This thesis presents the course structure, including connection to disciplinary principles, its affordances for community and collaboration and its support of individual differentiated learning and collective epistemology. It offers design principles for scripting and orchestrating collective inquiry designs for MOOCS and higher education courses.

University of Toronto2016

From Seminar to Lecture to MOOC: Scripting and Orchestration at Scale

Stian Haklev

University of Toronto2016