What is it about?
We introduce a data-driven method that turns real student mistakes into wrong answer options for multiple-choice questions. By using authentic errors, such as common misspellings, these distractors become more realistic and challenging. This makes practice with multiple-choice questions not only more engaging but also more effective for long-term learning. Our approach supports adaptive retrieval practice, helping students strengthen memory and improve spelling in a scalable way.
Featured Image
Photo by Glenn Carstens-Peters on Unsplash
Why is it important?
What makes this work unique is that it uses real learner mistakes to create multiple-choice distractors. Instead of assuming what kinds of mistakes students make, our method captures their actual misconceptions, making practice more authentic and challenging. This approach is timely because today’s learning platforms collect vast amounts of student response data, allowing these distractors to be generated automatically and at scale. By aligning questions with genuine error patterns, this method turns multiple-choice practice into a more effective tool for long-term learning.
Perspectives
My interest lies in how people learn and in designing practical tools that make a real difference for students. I like seeing how small mistakes can actually be useful, because they reveal so much about the learning process. This article shows how those mistakes can be turned into something constructive: better MC-practice questions that support learning more effectively.
Myrthe Braam
MemoryLab
Read the Original
This page is a summary of: Generating Competitive Distractors from Student Error Data, July 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3698205.3733945.
You can read the full text:
Contributors
The following have contributed to this page
