Using Machine Learning Methods to Understand Students' Performance in an Engineering Course

Machine learning methods were applied to analyze students' responses to clicker questions and individual exam questions. It was found that students who performed poorly in a sub-set of clicker questions tend to not do well in an exam question that requires analytical thinking skills (cognitivel...

Full description

Saved in:
Bibliographic Details
Main Authors: Kwan, Wei Lek, Pee, Gim-Yang Maggie, Koh, Li Ling Apple, Tan, Mei Xuan
Format: Conference Proceeding
Language:English
Subjects:
analytical thinking
Conferences
engineering
Engineering education
Machine learning
student learning
undergraduate
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning methods were applied to analyze students' responses to clicker questions and individual exam questions. It was found that students who performed poorly in a sub-set of clicker questions tend to not do well in an exam question that requires analytical thinking skills (cognitively demanding) even though they fare well in other application type (procedurally focused) questions. We conjecture that such students can be identified early using clicker questions to facilitate appropriate interventions.
ISSN:2165-9567
DOI:10.1109/EDUCON52537.2022.9766744