Document Type

Article

Domestic/International

Domestic

Location

Connecticut College

Publication Date

2026

Abstract

Teachers can't always tell when a student is confused. A student might look like they're paying attention but actually be lost and too nervous to ask for help. This summer, I worked with Professor William Tarimo and my research partner, Elle Hickman, to see if an affordable headband could help identify that. Most brain research uses expensive equipment in a lab, so we wanted to see if a $400 headband that anyone can buy could do something similar. The headband records EEG, which measures the electrical activity in the brain. Eight students wore the headband while we collected data on five mental states: confusion, boredom, mind-wandering, problem-solving, and engagement. I cleaned the data using Python and loaded it into Splunk, a data platform. Then, I tested four machine learning models to see which one could identify these mental states the best. Random Forest performed the best, with 91.22% accuracy. One model scored only 22%, but I later found out that the problem was how we prepared the data, not the model itself. We haven't tested the headband in a real classroom yet, so that's our next step. We want to find out if this technology could help teachers recognize when students are struggling and need help.

Download
COinS
 

The views expressed in this paper are solely those of the author.