# A Replication Study on Code Comprehension and Expertise using Lightweight Biometric Sensors

## TL;DR

This study replicates previous fMRI-based research on code comprehension by using lightweight biometric sensors, demonstrating high accuracy in task recognition but no correlation with expertise levels.

## Contribution

It introduces a lightweight biometric sensor approach for classifying code comprehension tasks, offering a practical alternative to fMRI with comparable accuracy.

## Key findings

- Heart signals alone achieved 87% accuracy in task classification.
- No significant correlation found between expertise and classifier performance.
- Lightweight sensors can effectively recognize comprehension tasks.

## Abstract

Code comprehension has been recently investigated from physiological and cognitive perspectives through the use of medical imaging. Floyd et al (i.e., the original study) used fMRI to classify the type of comprehension tasks performed by developers and relate such results to their expertise. We replicate the original study using lightweight biometrics sensors which participants (28 undergrads in computer science) wore when performing comprehension tasks on source code and natural language prose. We developed machine learning models to automatically identify what kind of tasks developers are working on leveraging their brain-, heart-, and skin-related signals. The best improvement over the original study performance is achieved using solely the heart signal obtained through a single device (BAC 87% vs. 79.1%). Differently from the original study, we were not able to observe a correlation between the participants' expertise and the classifier performance (tau = 0.16, p = 0.31). Our findings show that lightweight biometric sensors can be used to accurately recognize comprehension tasks opening interesting scenarios for research and practice.