Research group

Machine Learning Methods in Software Engineering

Code Style Embeddings

Kovalenko VladimirActive

This project is aimed at designing a system that builds numerical representations of developers' individual coding styles in an unsupervised manner, based on data from version control.

Building embeddings of individual code style is one way to enable team collaboration tools to detect and track knowledge transfer processes in teams. While it looks as a far-fetched goal, this project is our take on this problem.

The paper is to appear in CHASE 2020 proceedings.

Participants

Bogomolov Egor
Bogomolov Egor
Kovalenko Vladimir
Kovalenko Vladimir

Publications

Building Implicit Vector Representations of Individual Coding Style

June 2020

Vladimir Kovalenko, Egor Bogomolov, Timofey Bryksin, Alberto Bacchelli

Read more

Authorship Attribution of Source Code: A Language-Agnostic Approach and Applicability in Software Engineering

February 2020

Egor Bogomolov, Vladimir Kovalenko, Alberto Bacchelli, Timofey Bryksin

Read more