Bug Prediction Using Source Code Embedding Based on Doc2Vec

TL;DR

This paper introduces a source code embedding method based on Doc2Vec and ASTs, demonstrating improved bug prediction accuracy over traditional code metrics across various machine learning models.

Contribution

It presents a novel source code representation using AST-based Doc2Vec embeddings for bug prediction, outperforming metric-based features.

Findings

Embedding improves bug prediction accuracy in most cases

Embedding is at least as effective as code metrics alone

Various machine learning models benefit from the embedding

Abstract

Bug prediction is a resource demanding task that is hard to automate using static source code analysis. In many fields of computer science, machine learning has proven to be extremely useful in tasks like this, however, for it to work we need a way to use source code as input. We propose a simple, but meaningful representation for source code based on its abstract syntax tree and the Doc2Vec embedding algorithm. This representation maps the source code to a fixed length vector which can be used for various upstream tasks -- one of which is bug prediction. We measured this approach's validity by itself and its effectiveness compared to bug prediction based solely on code metrics. We also experimented on numerous machine learning approaches to check the connection between different embedding parameters with different machine learning models. Our results show that this representation provides meaningful information as it improves the bug prediction accuracy in most cases, and is always at least as good as only using code metrics as features.