Replication package for the paper: "Machine Learning for the Identification and Classification of Technical Debt Types on StackOverflow Discussions"

This is the replication package for the article "Machine Learning for the Identification and Classification of Technical Debt Types on StackOverflow Discussions". The article was published in the Research Track of the third Brazilian Workshop on Intelligent Software Engineering (ISE'23).

The replication package consists of 8 files:
1) dataset.csv, 2) code_anayses.ipynb and 3) example_test_balanced.csv and the others are results of word cloud generation.

In dataset.csv, we provide the data for future replications.

In code_anayses.ipynb, we provide the code we use to arrive at the results.

In example_test_balanced.csv, we provide an example input dataset for training the models.

For future references in this article, please contact lead author Eliakim Gama, or one of the co-authors.