This repository contains all our exploration on the use of machine learning methods to automatically recommend tags for software repositories.
It currently contains the following folders:
data-preparation: Our scripts for pre-processing the data, the data containing rules for preprocessing tags and generating sub-topics. Also, we include the final dataset of preprocessed sub-topics along with their featured Github topics and set of aliases.machine-learning: Our python scripts for training various machine-learning-based algorithms.
The paper can be found on ArXiv: link