Predicting Students' Exam Scores Using Physiological Signals

TL;DR

This study investigates the correlation between physiological stress signals and exam performance, demonstrating that machine learning models can predict students' grades based on signals like skin temperature, heart rate, and electrodermal activity.

Contribution

It introduces a method to predict exam scores from physiological signals using machine learning, which is a novel approach in educational performance analysis.

Findings

Achieved up to 0.81 ROC-AUC in grade prediction

Used physiological signals to classify higher or lower exam scores

Applied multiple classifiers with k-nearest neighbor performing best

Abstract

While acute stress has been shown to have both positive and negative effects on performance, not much is known about the impacts of stress on students grades during examinations. To answer this question, we examined whether a correlation could be found between physiological stress signals and exam performance. We conducted this study using multiple physiological signals of ten undergraduate students over three different exams. The study focused on three signals, i.e., skin temperature, heart rate, and electrodermal activity. We extracted statistics as features and fed them into a variety of binary classifiers to predict relatively higher or lower grades. Experimental results showed up to 0.81 ROC-AUC with k-nearest neighbor algorithm among various machine learning algorithms.