Can AI prediction dashboards help online groups?
Combining AI performance prediction with learning analytics reshaped analysis of online graduate groups' collaboration in an engineering course.
Source
Integration of artificial intelligence performance prediction and learning analytics to improve student learning in online engineering course
What they did
In an eight-week online graduate course, sixty-two students worked in fifteen groups on weekly collaborative writing. Researchers gathered discussion logs, applied AI-supported performance prediction and analytics, and analysed social-network measures plus students' end-of-course reflections.
What they found
Most social-network metrics differed significantly across analytic comparisons, including density. The integrated approach is framed as a way to identify at-risk students and support instructional decision-making during online collaborative work.
The limits
What it doesn't show
Findings come from one graduate engineering course rather than a multi-institution randomised trial. Predictive analytics are decision aids, not guarantees of later achievement for every learner.
Key terms
- AI performance prediction
- Models that estimate learners' likely performance to flag risk and guide support.
- Learning analytics
- Collecting and analysing learner data to understand and improve learning processes.
- Social network analysis (SNA)
- Methods that quantify relationships and interaction structure within groups.
- Collaborative writing
- Joint text production where groups plan, draft, and revise together.
- At-risk students
- Learners identified as likely to struggle without timely instructional support.
Flashcards
Want these cards to stick?
Save the deck to NoteFren and study it with spaced repetition.
Quiz yourself
How many graduate students participated?
Common questions
How many students participated?
62 graduate students (43 master's and 19 doctoral).
How were they organised?
Into 15 mixed groups of four to five.
How long was the course?
Eight weeks online in summer 2022.
What process data were analysed?
Among other sources, 105 group discussion files across seven weeks.
More on Online learning