Dropout prediction in MOOCs using learner activity features
Halawa, Sherif · Greene, Daniel · Mitchell, John

Alternate titleIssue No.37 Experiences and best practices in and around MOOCs
PublishedFebruary 2014
JournaleLearning Papers
Volume 37, Issue March 2014, Pages 1-10
Publisherelearningeuropa.info
Original PublicationEMOOCS 2014 conference
EditorsUllmo, Pierre-Antoine and Koskinen, Tapio
CountrySpain

ABSTRACT
Learners join a course with the motivation to persist for some or the entire course, but various factors, such as attrition or lack of satisfaction, can lead them to disengage or totally drop out. Educational interventions targeting such risk factors can help reduce dropout rates. However, intervention design requires the ability to predict dropouts accurately and early enough to allow for timely intervention delivery. In this paper, we present a dropout predictor that uses student activity features to predict which students have a high risk of dropout. The predictor succeeds in red-flagging 40% - 50% of dropouts while they are still active. An additional 40% - 45% are red-flagged within 14 days of absence from the course.

Keywords formative assessment · learning analytics · learning design · orchestration · teacher inquiry into student learning

Published atBarcelona
ISSN1887-1542
RefereedYes
Rightsby-nc-nd/3.0
URLhttp://openeducationeuropa.eu/en/article/Dropout-Prediction-in-MOOCs-using-Learner-Activity-Features?paper=136477
Export optionsBibTex · EndNote · Tagged XML · Google Scholar



AVAILABLE FILES
In_depth_37_1 (1).pdf · 370KB222 downloads



Viewed by 124 distinct readers




CLOUD COMMUNITY REVIEWS

The evaluations below represent the judgements of our readers and do not necessarily reflect the opinions of the Cloud editors.

Click a star to be the first to rate this document


POST A COMMENT
SIMILAR RECORDS

Early prediction and variable importance of certificate accomplishment in a MOOC
Ruipérez-Valiente, José A.; Cobos, Ruth; Muñoz-Merino, Pedro J.; Andujar, Álvaro; et al.
The emergence of MOOCs (Massive Open Online Courses) makes available big amounts of data about students' interaction with online educational platforms. This allows for the possibility of making predictions about future ...
Match: prediction; learning analytics; Spain

Driving student motivation in MOOCs through a conceptual activity-motivation framework
Khalil, Mohammad; Ebner, Martin
Massive Open Online Courses (MOOCs) require students’ commitment and engagement to earn the completion, certified or passing status. This study presents a conceptual Learning Analytics Activity-Motivation framework ...
Match: activity; learning analytics

Designing for educational technology to enhance the experience of learners in distance education: How Open Educational Resources, learning design and Moocs are influencing learning
Scanlon, Eileen; McAndrew, Patrick; O'Shea, Tim
The area of learning has a justifiable claim to be a special case in how it can be enhanced or supported by technology. In areas such as commerce and web design the aim is usually to ensure efficiency and support ...
Match: learning analytics; learning design

Weekly predicting the at-risk MOOC learners using dominance-based rough set approach
Bouzayane, Sarra; Saad, Inès; Kloos, Carlos Delgado; Jermann, Patrick; et al.
This paper proposes a method based on the Dominance-based Rough Set Approach (DRSA) to predict the learners who are likely to drop out the course during the next week of the MOOC (Massive Open Online Course) based on ...
Match: prediction; Spain

The EMMA experience. Emerging patterns and factors for success
De Rosa, Rosanna; Ferrari, Chiara; Kerr, Ruth; Kloos, Carlos Delgado; et al.
Since 2008, when the first experiment with MOOCs took place, much has been said, written and explored. However, almost ten years later we are unable to say whether MOOCs are really a desirable learning experience and, ...
Match: learning analytics; Spain

Does gamification in MOOC discussion forums work?
Reischer, Matthias; Khalil, Mohammad; Ebner, Martin; Kloos, Carlos Delgado; et al.
Massive Open Online Courses (MOOCs) are a new form of learning environment aimed towards accessibility and openness using contemporary technologies. One of the MOOC's key features is the social interaction which usually ...
Match: learning analytics; Spain

Diseño de un sistema de apoyo a la regulación social del aprendizaje en los xMOOC
Garcia, Iolanda; Barberà, Elena; Maina, Marcelo
Esta investigación tiene como objetivo estudiar los procesos de regulación del aprendizaje, atendiendo tanto a su dimensión individual como social, en entornos de xMOOC. En concreto,se propone analizar cómo los ...
Match: learning design; Spain

Conversations from south of the equator: Challenges and opportunities in OER across Broader Oceania
James, Rosalind; Bossu, Carina
Recent decades have witnessed a number of fundamental structural shifts, both internally within the higher education academy and external to it, that have transformed the character of universities. A universal, ...
Match: learning design; Spain

Design for collective intelligence: Pop-up communities in MOOCs
Garreta-Domingo, Muriel; Sloep, Peter B.; Hérnandez-Leo, Davinia; Mor, Yishay
Many current authors point toward the heightening of networked individualism and how this affects community creation and engagement. This trend poses strong challenges to the potential beneficial effects of collective ...
Match: learning design; Spain

Learning from open design: Running a learning design MOOC
McAndrew, Patrick; Koskinen, Tapio; Mor, Yishay
Massively Open Online Courses (MOOCs) give an opportunity for providing access to subjects of mass interest but also allow more niche subjects (Beavon, Commas- Quinn, de los Arcos & Hauck, 2013) to reach a larger ...
Match: learning design; Spain