Data for Bachelor Thesis "Identifying discussions on a topic: Using machine learning algorithms to detect fairness issues of software developers on Stack Exchange"

The code contains the BERTopic model used for the Bachelor Thesis "Identifying discussions on a topic: Using machine learning algorithms to detect fairness issues of software developers on Stack Exchange". It further contains the code used to classify the documents, as well as loading, saving and filtering excel files.The excel files "FirstRun" and "SecondRun" contain a more detailed explanation themselves. Generally speaking they provide the list of identified fairness posts for the corresponding runs of the BERTopic model, as described in the thesis.