Posts tagged edx

Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework

This paper is presented at the Fourth (2017) ACM Conference on Learning @ Scale in Cambridge (MA), USA, April 20–21, 2017.


In this paper, we demonstrate a first-of-its-kind adaptive intervention in a MOOC utilizing real-time clickstream data and a novel machine learned model of behavior. We detail how we
augmented the edX platform with the capabilities necessary to support this type of intervention which required both tracking learners’ behaviors in real-time and dynamically adapting content based on each learner’s individual clickstream history. Our chosen pilot intervention was in the category of adaptive pathways and courseware and took the form of a navigational suggestion appearing at the bottom of every non-forum content page in the course. We designed our pilot intervention to help students more efficiently navigate their way through a MOOC by predicting the next page they were likely to spend significant time on and allowing them to jump directly to that page. While interventions which attempt to optimize for learner achievement are candidates for this adaptive framework, behavior prediction has the benefit of not requiring causal assumptions to be made in its suggestions. We present a novel extension of a behavioral model that takes into account students’ time spent on pages and forecasts the same. Several approaches to representing time using Recurrent Neural Networks are evaluated and compared to baselines without time, including a basic n-gram model. Finally, we discuss design considerations and handling of edge cases for real-time deployment, including considerations for training a machine learned model on a previous offering of a course for use in a subsequent offering where courseware may have changed. This work opens the door to broad experimentation with adaptivity and serves as a first example of delivering a data-driven personalized learning experience in a MOOC.


Adaptivity; Personalization; Real-time intervention; MOOC; RNN; Behavioral modeling; Navigational efficiency; edX


Zachary A. Pardos, Steven Tang, Daniel Davis, and Christopher Vu Le. 2017. Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. In Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale (L@S ’17). ACM, New York, NY, USA, 23-32. DOI:


Research Seminar: Data Science Speeding up the Online learning curve

Open & Online education is a growing force in higher education. Platforms like EdX and Coursera offer a broad spectrum of Massive Open Online Courses. How do we keep learners engaged throughout a course and how do we assess if leaning goals have been achieved? The massive amount of data, produced by learners inside and outside the Massive Open Online Courses and the challenges for online assessment makes Online education a very interesting field for data science research. In this DDS seminar we will explore the research questions around learning analytics, gamification and online assessment.

How can we build comprehensive learner models that provide fine-grained insights into learners’ abilities, motivations, behaviour, knowledge and learning curves? For example a gaze-based indicator of students’ attention in a MOOC video lecture is proposed to define “with-me-ness” at two levels: perceptual, following teacher’s deictic acts; and conceptual, following teacher discourse.

Experiences  of gamification in the classroom give us food for thought for the use of gamification in the online learning environment. How can we use game-based learning to improve the learning outcomes? Assessment in online courses is now often done by multiple choice tests, but many instructors feel a need for automated assessment of “open” answers, designs, programs or other student materials. How can we achieve this? Can natural language processing and machine learning methods enhance online assignments and peer reviews? Will you join us for speeding up the Online learning curve?


Below you will find the overall program of the Research Seminar. For more information about the program and to register, please visit the seminar website.

  • 9.30   Welcome/coffee
  • 10.00  Opening by Claudia Hauff
  • 10.15  Kshitij Sharma – EPFL | École polytechnique fédérale de Lausanne
    “Looking THROUGH versus looking AT”
  • 10.35  Alexandru Iosup – Delft University of Technology
    “Gamification in the classroom”
  • 10.55 Markus Krause – Leibniz Universität Hannover
    “Learning at Scale: Promises, Reality, and Vision”
  • 11.15  Coffee Break
  • 11.45  Heide Lukosch – Delft University of Technology
    “Game-based learning”
  • 12.05  Eelco Visser – Delft University of Technology
    “Massive Online Assessment – beyond multiple choice”
  • 12.25  Panel discussion followed by closing remarks by Claudia Hauff
  • 13.00  Lunch with posters by companies and researchers
  • 14:00 End of program, start of the Education Seminar

Date: Moday March 9th | Time: 9:30 – 14:00 h | location: Culture Centre

© 2011 TU Delft