Automatic Code Review by Learning the Revision of Source Code

Shi, Shuting; Li, Ming; Lo, David; Thung, Ferdian; Huo, Xuan

doi:10.1609/aaai.v33i01.33014910

Cited by 39 publications

(36 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies have been conducted to analyze source codes such as generating pseudocode from source code [7], identifying topics in source codes [8], source code vulnerability analysis [9], code suggestion [10], classifying source codes according to their functionalities [11], clustering of source codes [12], code review [13], source code author identification [14] and summarization of code fragments [15]. Although all these studies used source codes as training dataset for learning task, they did not focus on identifying the languages of source codes.…”

Section: Related Workmentioning

confidence: 99%

Comparison of Image-Based and Text-Based Source Code Classification Using Deep Learning

et al. 2020

View full text Add to dashboard Cite

Source code classification (SCC) is a task to assign codes into different categories according to a criterion such as according to their functionalities, programming languages or vulnerabilities. Many source code archives are organized according to the programming languages, and thereby, the desired code fragments can be easily accessed by searching within the archive. However, manually organizing source code archives by field experts is labor intensive and impractical because of the fastgrowing available source codes. Therefore, this study proposes new convolutional neural network (CNN) architectures to build source code classifiers that automatically identify programming languages from source codes. This is the first study in which the performances of deep learning algorithms on programming language identification are compared on both image and text files. In this study, the experiments are performed on three source code datasets to identify eight programming languages, including C, C++, C# , Go, Python, Ruby, Rust, and Java. The comparative results indicate that although textbased SCC and image-based SCC approaches achieve very high ( > 93.5% ) and similar accuracies, text-based classification has significantly better performance in terms of execution time.

show abstract

Section: Related Workmentioning

confidence: 99%

Comparison of Image-Based and Text-Based Source Code Classification Using Deep Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Wei and Li (2017) studied software functional clone detection by applying a novel tree-based LSTM model, which is able to exploit the lexical and syntactical information from source code. Shi et al (2019) proposed a specific network to employ autoencoder to learn the feature of revision from an original-new source codes pair. There are also some work using deep learning models to identify buggy source code according to bug reports.…”

Section: Related Workmentioning

confidence: 99%

Control Flow Graph Embedding Based on Multi-Instance Decomposition for Bug Localization

Huo

2020

AAAI

Self Cite

View full text Add to dashboard Cite

During software maintenance, bug report is an effective way to identify potential bugs hidden in a software system. It is a great challenge to automatically locate the potential buggy source code according to a bug report. Traditional approaches usually represent bug reports and source code from a lexical perspective to measure their similarities. Recently, some deep learning models are proposed to learn the unified features by exploiting the local and sequential nature, which overcomes the difficulty in modeling the difference between natural and programming languages. However, only considering local and sequential information from one dimension is not enough to represent the semantics, some multi-dimension information such as structural and functional nature that carries additional semantics has not been well-captured. Such information beyond the lexical and structural terms is extremely vital in modeling program functionalities and behaviors, leading to a better representation for identifying buggy source code. In this paper, we propose a novel model named CG-CNN, which is a multi-instance learning framework that enhances the unified features for bug localization by exploiting structural and sequential nature from the control flow graph. Experimental results on widely-used software projects demonstrate the effectiveness of our proposed CG-CNN model.

show abstract

“…A recent work, by Toufique et al [9], uses Sentiment Analysis on code review to determine if the reviews are positive, neutral or negative comments. Shi et al [10] presents a deep learning-based model that uses source codes that are before modification and after modification. The model could determine if the submitted code changes are likely to be approved or rejected by the project administrators.…”

Section: Related Work a Automating Code Reviewmentioning

confidence: 99%

CORE: Automating Review Recommendation for Code Changes

Siow

Gao

Fan

et al. 2020

2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)

View full text Add to dashboard Cite

Code review is a common process that is used by developers, in which a reviewer provides useful comments or points out defects in the submitted source code changes via pull request. Code review has been widely used for both industry and open-source projects due to its capacity in early defect identification, project maintenance, and code improvement. With rapid updates on project developments, code review becomes a non-trivial and labor-intensive task for reviewers. Thus, an automated code review engine can be beneficial and useful for project development in practice. Although there exist prior studies on automating the code review process by adopting static analysis tools or deep learning techniques, they often require external sources such as partial or full source code for accurate review suggestion. In this paper, we aim at automating the code review process only based on code changes and the corresponding reviews but with better performance.The hinge of accurate code review suggestion is to learn good representations for both code changes and reviews. To achieve this with limited source, we design a multi-level embedding (i.e., word embedding and character embedding) approachto represent the semantics provided by code changes and reviews.The embeddings are then well trained through a proposed attentional deep learning model, as a whole named CORE. We evaluate the effectiveness of CORE on code changes and reviews collected from 19 popular Java projects hosted on Github. Experimental results show that our model CORE can achieve significantly better performance than the state-of-the-art model (DeepMem), with an increase of 131.03% in terms of Recall@10 and 150.69% in terms of Mean Reciprocal Rank. Qualitative general word analysis among project developers also demonstrates the performance of CORE in automating code review.

show abstract

Automatic Code Review by Learning the Revision of Source Code

Cited by 39 publications

References 21 publications

Comparison of Image-Based and Text-Based Source Code Classification Using Deep Learning

Comparison of Image-Based and Text-Based Source Code Classification Using Deep Learning

Control Flow Graph Embedding Based on Multi-Instance Decomposition for Bug Localization

CORE: Automating Review Recommendation for Code Changes

Contact Info

Product

Resources

About