Interests
My interests are machine learning applications for code maintenance and evolution, source code analysis, software privacy, medical software engineering and bioinformatics.
My name is Cody Watson, I am a PhD student at the College of William and Mary
and am being advised by Dr. Denys Poshyvanyk. We are focusing on deep learning applications to solve software engineering tasks.
My interests are machine learning applications for code maintenance and evolution, source code analysis, software privacy, medical software engineering and bioinformatics.
Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, and Denys Poshyvanyk. 2018. Deep learning similarities from different representations of source code. In Proceedings of the 15th International Conference on Mining Software Repositories (MSR '18). ACM, New York, NY, USA, 542-553. DOI: https://doi.org/10.1145/3196398.3196431
This paper assesses the similarity between different representations of source code. These representations can be leveraged for SE tasks such as clone detection, impact analysis, refactoring, ect. We leverage deep learning, rather than manual feature engineering, to determine code representations that are similar.
Michele Tufano, Cody Watson, Gabriele Bavota, Massimiliano Di Penta, Martin White, and Denys Poshyvanyk. 2018. An empirical investigation into learning bug-fixing patches in the wild via neural machine translation. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering (ASE 2018). ACM, New York, NY, USA, 832-837. DOI: https://doi.org/10.1145/3238147.3240732
This paper mines GitHub for bug-fixing commits and extracts methods out of those commits that were changed. Taking the method before and after the bug fix gives us training data to a deep learning RNN encoder-decoder architecture. The model is able to predict bug fixes for unseen methods in at least 9% of the cases.
Kevin Moran, Cody Watson, John Hoskins, George Purnell, and Denys Poshyvanyk. 2018. Detecting and summarizing GUI changes in evolving mobile apps. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering (ASE 2018). ACM, New York, NY, USA, 543-553. DOI: https://doi.org/10.1145/3238147.3238203
This paper implements a fully automated approach, called GCAT, which captures and reports GUI changes as mobile applications develop. This approach combines computer vision techniques with natural language processing to summarize GUI changes between successive commits or releases of a mobile application. We also perform a user study that showed GCAT outperformed developers in detecting and classifying GUI changes.
Watson, C., "Pymethyl: A Bioinformatic Approach to Methylation Patterns and their Epigenetic Effects on Risk of Breast Cancer" in SIAM Conference on Computational Science and Engineering (SIAM '15). March 14-18, 2015.
This talk focused on aligning full human genomes to discover methylation pattern differences. In lamens terms, methylation is a tool the body uses for increased / decreased expression of particular genes. Understanding these patterns can unlock epigenetic solutions for particular medical conditions.
I have a strong passion for the education of future generation software engineers. I want to help equip and teach them the skills they need to continue advancing the field of computer science and aiding in future research developments. I also want to extend my ability to teach a variety of classes inlcuding securing software, bioinformatics, genomic data analysis, deep learning in software engineering, mobile software engineering and more. I have also had the pleasure to mentor both undergraduate and graduate level students in their research endeavors. I look to continue fostering this passion for teaching and will push myself to be a better educator. I have lead research projects for undergraduate software engineering courses (CSci 435), research projects for graduate software engineering courses (Csci 635) and guest lectured multiple times for undergraduate software engineering classes (Csci 435).
I was born and raised in Chicago, IL and attended Lake Forest Academy. Afterwards, I recieved my B.S. in Biology and B.A. in Computer Science from Wofford College in South Carolina. Under the mentorship of Dr. Angela Shiflet and Dr. George Shiflet, my undergraduate research consisted of bioinformatic and genomic software development. Also, in my undergraduate career, I worked with Dr. Jose Russo at Fox Chase Cancer Center where we worked on genomic software for studying breast cancer. After graduating college, I applied and was accepted to William and Mary where I am currently pursuing my PhD under Dr. Poshyvanyk.
I also love collaboration with other sciences, particularly chemistry and biology, so don't be afraid to send me an email for research also involing other fields. On a personal note, I am married to my loving and supporting wife and we enjoy hiking, our puppy and long walks through Colonial Williamsburg.
Please feel free to contact me via email. I will always try to answer questions or requests to the best of my ability