University of Twente Student Theses

Login
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.

[img] 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