2016挖掘软件库机器学习专题会议 2016 Special Session on Machine Learning for Mining Software Repositories

征稿已开启

已截稿

注册已开启

已截止

活动简介

Recently machine learning has started to play a key role in facilitating research in mining diverse software repositories. Open source software systems are becoming ever larger, with many components available online. Available to download are not only source code, but also messages exchanged by the contributors, defect databases and new features requests. All this information amounts to gigabytes of mostly text data that is hard to analyze and summarize efficiently.
Many well-known machine learning techniques can be used to mine this information to make better decisions related to software systems maintenance, and to provide insights about software design and automate triage of defects. It is important that researchers share datasets, methods and procedures and results that can be easily reproduced.
The goal of this special session is to bring together researchers from software engineering and machine learning to exchange ideas about the current state of practice in mining software repositories.

征稿信息

重要日期

2016-08-06

初稿截稿日期

2016-10-01

终稿截稿日期

征稿范围

Some topics relevant to this special session include but are not limited to:

Approaches, applications, and tools for software repository mining
Classification, and prediction of bugs based on analysis of software repositories
Mining code fragments
Mining bug reports for fix-time prediction
Mining bug reports for re-opened bug prediction
Mining bug reports for blocking bug prediction
Mining bug reports for severity/priority prediction
Mining bug reports for delay prediction in integration of resolved issues into releases
Mining bug reports for bug triaging
Mining bug reports for duplicate bug detection
Predictive models for project risk assessment
Social network analysis for software repositories
Sentiment analysis for question-answering sites such as Stack OverflowRecommendation systems
Mining software licensing and copyrights
Mining execution traces and commit logs
Sentiment Analysis on software engineering artifacts