Understanding Developer-Analyzer Interactions in Code Reviews

Static code analyzers are now a common part of the codereview process. These automated tools integrate into the code review process by commenting on code changes and suggesting improvements, in the same way as human reviewers. The comments made by static analyzers often trigger a conversation betwee...

Full description

Saved in:
Bibliographic Details
Main Authors: Schaef, Martin, Cirisci, Berk, Luo, Linghui, Mansur, Muhammad Numair, Tripp, Omer, Sanchez, Daniel, Zhou, Qiang, Zafar, Muhammad Bilal
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Codes
Labeling
large language models
Oral communication
Reviews
sast
Software and its engineering > Software creation and management > Software verification and validation > Software defect analysis > Software testing and debugging
Software and its engineering > Software notations and tools > Software maintenance tools
Software maintenance
Software reliability
Software testing
static analysis
Training
Uncertainty
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Static code analyzers are now a common part of the codereview process. These automated tools integrate into the code review process by commenting on code changes and suggesting improvements, in the same way as human reviewers. The comments made by static analyzers often trigger a conversation between developers to align on if and how the issue should be fixed. Because developers rarely give feedback directly to the tool, understanding the sentiment and intent in the conversation triggered by the tool comments can be used to measure the usefulness of the static analyzer. In this paper, we report on an experiment where we use large language models to automatically label and categorize the sentiment and intent of such conversations triggered by static analyzer comments. Our experiment demonstrates that LLMs not only classify and interpret complex developer-analyzer conversations, but can be more accurate than human experts.
ISSN:2643-1572
DOI:10.1145/3691620.3695257