# Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study

arXiv: https://arxiv.org/abs/2303.06808 · HTML: https://mlsanity.com/paper/2303.06808/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [A Survey of Machine Learning for Big Code and Naturalness](https://mlsanity.com/paper/1709.06182/) (2017)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Natural Attack for Pre-trained Models of Code](https://mlsanity.com/paper/2201.08698/) (2022)
- [Self-Supervised Bug Detection and Repair](https://mlsanity.com/paper/2105.12787/) (2021)
- [Adversarial Robustness for Code](https://mlsanity.com/paper/2002.04694/) (2020)
- [Improving short text classification through global augmentation methods](https://mlsanity.com/paper/1907.03752/) (2019)
- [Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding](https://mlsanity.com/paper/2112.02268/) (2021)
- [How could Neural Networks understand Programs?](https://mlsanity.com/paper/2105.04297/) (2021)
- [Empirical Study of Transformers for Source Code](https://mlsanity.com/paper/2010.07987/) (2020)
- [A Search-Based Testing Framework for Deep Neural Networks of Source Code Embedding](https://mlsanity.com/paper/2101.07910/) (2021)
- [CodeS: Towards Code Model Generalization Under Distribution Shift](https://mlsanity.com/paper/2206.05480/) (2022)
- [CoCoFuzzing: Testing Neural Code Models with Coverage-Guided Fuzzing](https://mlsanity.com/paper/2106.09242/) (2021)

## Built on by (most cited first, 5 of 5)

- [Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://mlsanity.com/paper/2403.02990/) (2024)
- [Source Code Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2305.19915/) (2023)
- [Semantic-Preserving Transformations as Mutation Operators: A Study on Their Effectiveness in Defect Detection](https://mlsanity.com/paper/2503.23448/) (2025)
- [LLM-based Vulnerable Code Augmentation: Generate or Refactor?](https://mlsanity.com/paper/2512.08493/) (2025)
- [Learning Generalizable Multimodal Representations for Software Vulnerability Detection](https://mlsanity.com/paper/2604.25711/) (2026)

## Abstract (arXiv)

Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires massive high-quality training data to achieve the success of these applications. Data augmentation, a technique used to produce additional training data, is widely adopted in other domains (e.g. computer vision). However, the existing practice of data augmentation in source code learning is limited to simple syntax-preserved methods, such as code refactoring. In this paper, considering that source code can also be represented as text data, we take an early step to investigate the effectiveness of data augmentation methods originally designed for natural language texts in the context of source code learning. To this end, we focus on code classification tasks and conduct a comprehensive empirical study across four critical code problems and four DNN architectures to assess the effectiveness of 25 data augmentation methods. Our results reveal specific data augmentation methods that yield more accurate and robust models for source code learning. Additionally, we discover that the data augmentation methods remain beneficial even when they slightly break source code syntax.