Automatically Learning Patterns for Self-Admitted Technical Debt Removal

Abstract

DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

Self-admitted technical debt practices: a comparison between industry and open-source

“…Previous studies have related such evidence with software quality (Bavota and Russo, 2016;Wehaibi et al, 2016;da S. Maldonado et al, 2017a;Zampetti et al, 2018), by mining and analyzing related comments in the source code or elsewhere, e.g., in the issues (Xavier et al, 2020). However, while studies have been conducted to understand developers' perception of TD (Ernst et al, 2015), to identify strategies related to its introduction (Fucci et al, 2020) and removal (Bavota and Russo, 2016;da S. Maldonado et al, 2017a;Zampetti et al, 2018;Iammarino et al, 2019;Zampetti et al, 2020) so far there is limited empirical evidence on the reasons and circumstances in which developers admit TD under the form of a SATD comment, and how they cope with it beyond removal.…”

DebtFree: Minimizing Labeling Cost in Self-Admitted Technical Debt Identification using Semi-Supervised Learning

“…Each of these stages offers unique and separate challenges, each of which deserves extensive attention. Many of these steps have been extensively studied in the literature [15,16,17,30,35,37,38,53,84,85]. However, the labeling work of step 4 has been receiving scant attention.…”

Predictive Models in Software Engineering: Challenges and Opportunities

“…Five studies [95,257,289,308,319] concentrated on Self-Admitted Technical Debt(SATD) detection. Yan et al [308] applied Random Forest to automatically detect change-level SATDs from source code, and Zampetti et al [319] trained a deep learning model to learn patterns for remove useless SATD comments. Huang et al [95] used multiple predictive models, including SVM, kNN, and NLP algorithms for SATD detection.…”