# Towards Generation of Visual Attention Map for Source Code

## TL;DR

This paper proposes a framework to analyze programmers' gaze behavior in source code comprehension by comparing it with importance maps generated by attention models like code2vec, aiming to better understand and reflect component importance.

## Contribution

It introduces a novel conceptual framework that uses attention maps from models to quantify component importance and analyze gaze behavior during code comprehension.

## Key findings

- Preliminary experiment results show potential for aligning gaze data with attention-based importance.
- The framework offers a new approach to understanding source code comprehension processes.
- It bridges the gap between model-derived importance and human gaze behavior in programming.

## Abstract

Program comprehension is a dominant process in software development and maintenance. Experts are considered to comprehend the source code efficiently by directing their gaze, or attention, to important components in it. However, reflecting the importance of components is still a remaining issue in gaze behavior analysis for source code comprehension. Here we show a conceptual framework to compare the quantified importance of source code components with the gaze behavior of programmers. We use "attention" in attention models (e.g., code2vec) as the importance indices for source code components and evaluate programmers' gaze locations based on the quantified importance. In this report, we introduce the idea of our gaze behavior analysis using the attention map, and the results of a preliminary experiment.