Semantic Neighborhood Density and Eye Gaze Time in Human Programmer Attention

TL;DR

This study explores how the semantic similarity of words in source code, measured by Semantic Neighborhood Density, relates to the amount of human attention as indicated by eye gaze time, revealing that more semantically dense words attract longer gaze times especially when infrequent.

Contribution

The paper introduces the application of Semantic Neighborhood Density to source code and analyzes its relationship with human gaze behavior in programming tasks.

Findings

High SND words have longer gaze times, especially if infrequent.

SND and word frequency have limited predictive power for gaze time.

Semantic factors influence programmer attention in source code.

Abstract

This paper studies the relationship between human eye gaze time on words in source code and the Semantic Neighborhood Density (SND) of those words. Human eye gaze time is a popular way to quantify human attention such as the importance of words people read and the cognitive effort people exert. Meanwhile, SND is a measure of how similar a word is in meaning to other words in the same context. SND has a long history in Psychology research where it has been connected to eye gaze time in various domains and helps explain human cognitive factors such as confusion and quality of reading comprehension. But SND carries an unknown and potentially unique meaning in software engineering. In this paper, we compute SND for tokens in source code that people viewed in two previous eye-tracking experiments, one in C and one in Java. We conduct a model-free analysis for statistical relationships between SND and gaze time, and a model-based analysis for predictive power of SND to gaze time. We found that words with high SND tend to have higher gaze time then low SND words, especially for words that are uncommon (i.e., have low frequency). We also found SND and frequency to have a minor predictive power on gaze time, despite high levels of noise common in eye tracking data