Software systems have been playing important roles in business, scientific research, and our everyday lives. It is critical to improve both software productivity and quality, which are major challenges to software engineering researchers and practitioners. As developers work on a project, they leave behind many digital artifacts. These digital trails can provide insights into how software is developed and provide a rich source of information to help improve development practices. For instance, GitHub hosts more than 57M repositories, and is currently used by more than 20M developers. As another example, Stack Overflow has more than 3.9M registered users, 8.8M questions, and 41M comments. The productivity of software developers and testers can be improved using information from these repositories.
In recent years, intelligent software engineering has emerged as a promising means to address these challenges. In intelligent software engineering, Artificial Intelligence (AI) techniques (e.g., deep learning) have been frequently applied to discover knowledge or build intelligent tools from software artifacts (e.g., specifications, source code, documentations, execution logs, code commits and bug reports) to improve software quality and development process (e.g., to obtain the insights for the causes leading to poor software quality, and to help the managers optimize the resources for better productivity). And these techniques have shown a great success in addressing various software engineering problems (e.g., code generation, code recommendation, and bug fix and repair). Therefore, intelligent software engineering has attracted great attention in both software engineering and AI communities.
We invite the submission of high-quality papers describing original and significant work in all areas of intelligent software engineering including (but not limited to): 1) Methodological and technical foundations of intelligent software engineering, 2) Approaches and techniques for knowledge discovery in various software artefacts, and 3) Applications of AI techniques to facilitate specialized tasks in software engineering. We especially encourage submission of extended papers from the 18th National Software Application Conference (NASAC 2019). Topics of interest include but are not limited to:
A. Intelligent software engineering techniques
A1. AI models and techniques for software engineering
A2. Robust and highly scalable algorithms for mining ultra-large-scale software systems
A3. Explainable and actionable AI models
A4. Visualizing AI models
B. Knowledge discovery in software artefacts
B1. Mining software specifications
B2. Mining source code/code commits
B3. Mining execution traces and logs
B4. Mining bug and crash reports
B5. Mining Q&A and social data
C. Intelligent software engineering in specialized tasks
C1. AI techniques for software development and reuse
C2. AI techniques for software maintenance and evolution
C3. AI techniques for software testing and debugging
C4. AI techniques for open source ecosystem best practices
C5. AI techniques for software defect identification and characterization