Leveraging Learning Analytics to Enhance Early Student Intervention
Applying learning analytics can help universities identify at-risk students early on based on engagement metrics, tutorial attendance, and other measures. By avoiding common pitfalls and focusing on making analytics useful and accessible, institutions can improve student support and intervene effectively to enhance academic performance.
- Learning Analytics
- Student Intervention
- Academic Performance
- Engagement Metrics
- Early Warning System
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Using learning analytics to identify at-risk students within eight weeks of starting university: problems and opportunities Ms. Avril Dewar, Dr. David Hope & Professor Helen Cameron May 2015
Project Background Early academic performance predicts later academic performance very well We wanted to develop an early warning system that identifies student difficulty and disengagement before assessment 80% of the most at-risk (failing) candidates were identified by the model. There were large differences between the most and least at-risk students
Selection of Measures Engagement with routine tasks Completion of formative assessment Tutorial attendance Attendance at voluntary events/activities Virtual Learning Environment (VLE) exports (some) Time until first contact
Why some Learning Analytics (LA) measures failed Kitchen sink approach Visits to individual VLE pages Raw database export/inappropriate formatting Pattern of usage Information was only available visually (heat maps) and not in numerical format Time spent on pages, quizzes etc. Cannot currently be recorded accurately, too many extremes which skew the data
Making LA useful Simple Comprehensible Accessible Ease of scaling Doesn t replicate existing measures Discriminates between students Central storage
Things LA could provide but we dont use A mix of ethical and practical concerns IP addresses for location Discussion board content Time taken to answer individual questions At what point does your picture become too detailed?
Bad (Theoretical!) Scenarios Web traffic shows your student has been searching for essay-buying websites Your student is absent from class and claims to be at home, ill. But an IP address record shows they are not where they say they are Your student claims to be working hard, but records show they have never been to the library or accessed the course VLE
The Teacher-Student Relationship Knowing too much creates a conflict between your academic role and your duty of care Because very little attention is formally paid to how you get the information it can be very unclear how you should act Will your opinion of a student change if you know they are deceptive? How will you react if a student isn t coping but won t talk to you about it?
How Much is Too Much? Data on student activity can help enhance teaching and learning Policies often fail to reflect how large amounts of ordinary data can create a detailed picture of a student E.g. when and where student logs in a sophisticated tracking and monitoring system! We always aim to be conservative, rather than exhaustive in data acquisition
The Early warning project Open source training materials are currently being developed. We re partnering widely, including internationally, to disseminate the project If you would like a copy of the materials or for us to work with your data, please get in touch.
Any questions? Avril.Dewar@ed.ac.uk
