Retain: building a concept recommendation system that leverages spaced repetition to improve retention in educational settings
Subrahmanyam, Shilpa
Loading…
Permalink
https://hdl.handle.net/2142/97490
Description
Title
Retain: building a concept recommendation system that leverages spaced repetition to improve retention in educational settings
Author(s)
Subrahmanyam, Shilpa
Issue Date
2017-04-26
Director of Research (if dissertation) or Advisor (if thesis)
Zhai, ChengXiang
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
Spaced repetition
Education
Concept recommendation system
Abstract
There is a glaring lack of focus on long-term retention in today's educational paradigms. Moreover, research in the area of learning, memory, and specifically, promoting long-term retention has produced several robust and experimentally validated principles. A lot of this work can be leveraged to place some much-needed emphasis on long-term retention in educational settings.
One such principle is spaced repetition -- a technique that has been empirically proven to promote long-term retention. The applications of current spaced repetition algorithms are limited to atomic concepts -- concepts that don't have any conceptual dependencies. In order to apply current spaced repetition formulae to more general contexts, we need to develop a system that can take conceptual dependencies into account.
In this paper, we propose a framework called Retain that does exactly this. Retain is a system that can be used in virtually any educational context -- not just contexts that solely involve atomic concepts (i.e. learning vocabulary terms). It is a concept recommendation system that provides students with suggestions about when to review various concepts based on their understanding of parent concepts and the principle of spaced repetition. The results produced by Retain as well as the rules upon which Retain was built were evaluated by a group of teachers and were overwhelmingly favored over other concept recommendation baselines.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
