University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Fake it till you make it : exploring the usefulness of synthetic self-admitted technical debt datasets
Atanasov, Miroslav (2025) Fake it till you make it : exploring the usefulness of synthetic self-admitted technical debt datasets.
PDF
836kB |
Abstract: | This research investigates whether synthetic data augmentation improves machine learning models' performance in detecting and classifying Self-Admitted Technical Debt (SATD) from code comments. We evaluate the DebtHunter and PILOT models using both Maldonado et al.'s dataset as well as SATDAUG, an augmented dataset based on it. Ultimately, we show that this approach yields significant results by effectively addressing class imbalance issues that has previously hindered accurate detection and classification. |
Item Type: | Essay (Bachelor) |
Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
Subject: | 54 computer science |
Programme: | Computer Science BSc (56964) |
Link to this item: | https://purl.utwente.nl/essays/107561 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page