Utilising learning analytics for study success: A systematic review of five years of research (2013-17)
Yau, Jane Yin-Kim
;
Mah, Dana-Kristin
;
Ifenthaler, Dirk
Document Type:
|
Conference presentation
|
Year of publication:
|
2018
|
Conference title:
|
83. Tagung der Arbeitsgruppe für Empirische Pädagogische Forschung (AEPF)
|
Location of the conference venue:
|
Lüneburg, Germany
|
Date of the conference:
|
24-26.09.2018
|
Publication language:
|
English
|
Institution:
|
Business School > Wirtschaftspädagogik, Technologiebasiertes Instruktionsdesign (Ifenthaler 2015-)
|
Subject:
|
004 Computer science, internet
|
Abstract:
|
Learning Analytics (LA) use static and dynamic information about learners and learning environments, assessing, eliciting and analyzing it, for real-time modeling, prediction and optimization of learning processes, learning environments, as well as educational decision-making (Ifenthaler, 2015). Still, LA have been more commonly used in the higher education institutions within USA, Australia, and England whereas in other countries, the use of LA is still relatively rare (Ferguson et al., 2016). One way of motivating other institutions (in other countries) to adopt the use of LA is to demonstrate its potential use via empirical evidence in experimental studies published in scientific articles on the use of LA, which have successfully enhanced study success. There is relatively small amount of empirical evidence as well as systematic reviews on LA, prevention and intervention measures to increase study success in international studies (Ferguson & Clow, 2017) and therefore this gives rise to the motivation of our project.
The aim of the project “Utilizing Learning Analytics for Study Success” is to conduct a systematic review and construct a set of policies for higher education institutions to adopt LA capabilities into their existing learning environments. Precisely, the goal is to build a systematic review of empirical evidence demonstrating how learning analytics have been successful in facilitating student success in continuation and completion of their university courses both nationally and internationally. The research question is: Is it possible to identify a link between learning analytics and prevention and intervention measures to increase study success in international studies?
Our systematic review was conducted from 01-12/2017. We searched international databases including ACM Digital Library, Science Direct amongst others as well as in several high-impact related journals. Search terms included “Learning Analytics” in combination with “study success”, “retention”, “dropout prevention”, “course completion”, and “attrition”. 6220 articles were located and after duplicated papers were removed, 3163 were remaining. All of these abstracts of papers were screened and included in our systematic review according to our inclusion criteria: a) were situated in the higher education context, b) were published between 01/2013 and 12/2017, c) were published in English, d) presented either qualitative or quantitative findings and e) were peer-reviewed. The number of key studies identified was 374 then limited to 41 (due to substantiality of empirical evidence). The summary of identified empirical evidence is (from sources including Sclater and Mullan, (2017)):
1. Predictive accuracy are in terms of course completion, dropouts, achievement level, study achievement, total study time, interaction with colleagues, frequency of regular learning intervals, and number of downloads in the learning environment and can increase over time.
2. Reduction of dropout rates (11%) and prognosis of dropouts based on the course attended. 66% of vulnerable students have not completed their courses.
3. Strong correlation between CGPA (sometimes financial status also) and pre-set grades.
4. Positive relationship between student satisfaction with the use of the learning dashboard and their learning success.
5. 90% of learners were identified as at-risk with 98% confidence level.
6. Online learning systems are more reliable and can produce better prediction.
7. An index method was utilized which could make accurate predictions of dropout.
8. Positive outcomes on learning performance were achieved for the students who utilized the intervention program.
9. The engagement level and learning outcome were higher in the LA experimental group than in the control group.
10. Positive learning experiences via the use of a LA recommender.
Our future work include (1) conducting an interview study to determine the readiness of German higher education institutions towards LA and (2) providing policy recommendations to help institutions to progress to individual LA projects hence enhancing study success.
|
Search Authors in
You have found an error? Please let us know about your desired correction here: E-Mail
Actions (login required)
|
Show item |
|