Standard

Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. / Pardos, Zachary A.; Tang, Steven; Davis, Daniel; Vu Le, Christopher.

L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale. New York, NY : Association for Computing Machinery (ACM), 2017. p. 23-32.

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Harvard

Pardos, ZA, Tang, S, Davis, D & Vu Le, C 2017, Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. in L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale. Association for Computing Machinery (ACM), New York, NY, pp. 23-32, L@S '17 The Fourth (2017) ACM Conference on Learning @ Scale, Cambridge, United States, 20/04/17. https://doi.org/10.1145/3051457.3051471

APA

Pardos, Z. A., Tang, S., Davis, D., & Vu Le, C. (2017). Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. In L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale (pp. 23-32). New York, NY: Association for Computing Machinery (ACM). https://doi.org/10.1145/3051457.3051471

Vancouver

Pardos ZA, Tang S, Davis D, Vu Le C. Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. In L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale. New York, NY: Association for Computing Machinery (ACM). 2017. p. 23-32 https://doi.org/10.1145/3051457.3051471

Author

Pardos, Zachary A. ; Tang, Steven ; Davis, Daniel ; Vu Le, Christopher. / Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale. New York, NY : Association for Computing Machinery (ACM), 2017. pp. 23-32

BibTeX

@inproceedings{4a195ff8792147e1a73681caa2fc12c2,
title = "Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework",
abstract = "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.",
keywords = "Adaptivity, Personalization, Real-time intervention, MOOC, RNN, Behavioral modeling, Navigational efficiency, edX",
author = "Pardos, {Zachary A.} and Steven Tang and Daniel Davis and {Vu Le}, Christopher",
year = "2017",
doi = "10.1145/3051457.3051471",
language = "English",
pages = "23--32",
booktitle = "L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS

TY - GEN

T1 - Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework

AU - Pardos, Zachary A.

AU - Tang, Steven

AU - Davis, Daniel

AU - Vu Le, Christopher

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

KW - Adaptivity

KW - Personalization

KW - Real-time intervention

KW - MOOC

KW - RNN

KW - Behavioral modeling

KW - Navigational efficiency

KW - edX

U2 - 10.1145/3051457.3051471

DO - 10.1145/3051457.3051471

M3 - Conference contribution

SP - 23

EP - 32

BT - L@S'17 Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale

PB - Association for Computing Machinery (ACM)

CY - New York, NY

ER -

ID: 36754582