Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
How learning analytics can early predict under-achieving students in a blended medical education course
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences. Qassim University, Kingdom of Saudi Arabia.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
Number of Authors: 32017 (English)In: Medical teacher, ISSN 0142-159X, E-ISSN 1466-187X, Vol. 39, no 7, p. 757-767Article in journal (Refereed) Published
Abstract [en]

Aim: Learning analytics (LA) is an emerging discipline that aims at analyzing students' online data in order to improve the learning process and optimize learning environments. It has yet un-explored potential in the field of medical education, which can be particularly helpful in the early prediction and identification of under-achieving students. The aim of this study was to identify quantitative markers collected from students' online activities that may correlate with students' final performance and to investigate the possibility of predicting the potential risk of a student failing or dropping out of a course.Methods: This study included 133 students enrolled in a blended medical course where they were free to use the learning management system at their will. We extracted their online activity data using database queries and Moodle plugins. Data included logins, views, forums, time, formative assessment, and communications at different points of time. Five engagement indicators were also calculated which would reflect self-regulation and engagement. Students who scored below 5% over the passing mark were considered to be potentially at risk of under-achieving.Results: At the end of the course, we were able to predict the final grade with 63.5% accuracy, and identify 53.9% of at-risk students. Using a binary logistic model improved prediction to 80.8%. Using data recorded until the mid-course, prediction accuracy was 42.3%. The most important predictors were factors reflecting engagement of the students and the consistency of using the online resources.Conclusions: The analysis of students' online activities in a blended medical education course by means of LA techniques can help early predict underachieving students, and can be used as an early warning sign for timely intervention.

Place, publisher, year, edition, pages
2017. Vol. 39, no 7, p. 757-767
National Category
Computer and Information Sciences General Practice Educational Sciences
Research subject
Information Society
Identifiers
URN: urn:nbn:se:su:diva-145289DOI: 10.1080/0142159X.2017.1309376ISI: 000404352900010PubMedID: 28421894OAI: oai:DiVA.org:su-145289DiVA, id: diva2:1128386
Available from: 2017-07-25 Created: 2017-07-25 Last updated: 2018-09-24Bibliographically approved
In thesis
1. Using Learning Analytics to Understand and Support Collaborative Learning
Open this publication in new window or tab >>Using Learning Analytics to Understand and Support Collaborative Learning
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Learning analytics (LA) is a rapidly evolving research discipline that uses insights generated from data analysis to support learners and optimize both the learning process and learning environment. LA is driven by the availability of massive data records regarding learners, the revolutionary development of big data methods, cheaper and faster hardware, and the successful implementation of analytics in other domains. The prime objective of this thesis is to investigate the potential of learning analytics in understanding learning patterns and learners’ behavior in collaborative learning environments with the premise of improving teaching and learning. More specifically, the research questions comprise: How can learning analytics and social network analysis (SNA) reliably predict students’ performance using contextual, theory-based indicators, and how can social network analysis be used to analyze online collaborative learning, guide a data-driven intervention, and evaluate it. The research methods followed a structured process of data collection, preparation, exploration, and analysis. Students’ data were collected from the online learning management system using custom plugins and database queries. Data from different sources were assembled and verified, and corrupted records were eliminated. Descriptive statistics and visualizations were performed to summarize the data, plot variables’ distributions, and detect interesting patterns. Exploratory statistical analysis was conducted to explore trends and potential predictors, and to guide the selection of analysis methods. Using insights from these steps, different statistical and machine learning methods were applied to analyze the data. The results indicate that a reasonable number of underachieving students could be predicted early using self-regulation, engagement, and collaborative learning indicators. Visualizing collaborative learning interactions using SNA offered an easy-to-interpret overview of the status of collaboration, and mapped the roles played by teachers and students. SNA-based monitoring helped improve collaborative learning through a data-driven intervention. The combination of SNA visualization and mathematical analysis of students’ position, connectedness, and role in collaboration was found to help predict students’ performance with reasonable accuracy. The early prediction of performance offers a clear opportunity for the implementation of effective remedial strategies and facilitates improvements in learning. Furthermore, using SNA to monitor and improve collaborative learning could contribute to better learning and teaching.

Place, publisher, year, edition, pages
Stockholm: Department of Computer and Systems Sciences, Stockholm University, 2018. p. 143
Series
Report Series / Department of Computer & Systems Sciences, ISSN 1101-8526 ; 18-011
Keywords
Learning analytics, Social Network Analysis, Collaborative Learning, Medical Education, Interaction Analysis, Machine Learning
National Category
Computer Sciences
Research subject
Information Society
Identifiers
urn:nbn:se:su:diva-159479 (URN)978-91-7797-440-6 (ISBN)978-91-7797-441-3 (ISBN)
Public defence
2018-10-22, L70, NOD-huset Borgarfjordsgatan 12, Kista, 09:00 (English)
Opponent
Supervisors
Note

At the time of the doctoral defense, the following paper was unpublished and had a status as follows: Paper 4: Accepted.

Available from: 2018-09-27 Created: 2018-09-05 Last updated: 2018-09-27Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Saqr, MohammedFors, UnoTedre, Matti
By organisation
Department of Computer and Systems Sciences
In the same journal
Medical teacher
Computer and Information SciencesGeneral PracticeEducational Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 37 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf