Smelling smells using Deep Learning

We have two objectives to carry out this research. The first objective is to explore the feasibility of applying deep learning models to detect smells without extensive feature engineering, just by feeding the source code elements in tokenized form. Another goal of the work is to investigate the possibility of applying transfer-learning in the context of deep learning models for smell detection by investigating transferability of results between programming languages.

This repository contains supporting material of the experiment.