Unveiling the Technical Roles of GitHub Users

This dataset contains the scripts and dataset used in the study reported at <em>Unveiling the Technical Roles of GitHub Users</em> paper. The files are described in more detailed below: processed_ground_truth.csv: A CSV file with the information of the developers considered in the study. Due to privacy issues, we already preprocessed the dataset to remove identification clues. Please contact the authors in case you need the original one. processed_ground_truth_fullstack.csv: Same CSV file but with fullstack developers. script.ipynb: A Jupyter notebook with the scripts used in our study. Pipfile: The list of dependencies used to execute our script. This way you can replicate our study in an easier way (i.e., using virtual environments). bag-of-words-iterations: List of classifications results for differents bag of words parameters.