no code implementations • 16 May 2023 • Garima Malik, Mucahit Cevik, Ayşe Başar
This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification.
1 code implementation • 2 Nov 2022 • Hadi Jahanshahi, Mucahit Cevik, Kianoush Mousavi, Ayşe Başar
In this study, we develop a Markov decision process (MDP) model for an online bug triage task.
no code implementations • 18 Apr 2022 • Aysun Bozanta, Sean Berry, Mucahit Cevik, Beste Bulut, Deniz Yigit, Fahrettin F. Gonen, Ayşe Başar
We compare our approach with traditional clustering algorithms, which typically rely on generic distance metrics such as Euclidean distance, and image clustering approaches that aim to group data by capturing its visual patterns.
no code implementations • 2 Sep 2021 • Hadi Jahanshahi, Ozan Ozyegen, Mucahit Cevik, Beste Bulut, Deniz Yigit, Fahrettin F. Gonen, Ayşe Başar
In our experiments, we investigate the generalizability of the trained models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the benefits of incorporating product titles in multiple languages.
1 code implementation • 26 Apr 2021 • Hadi Jahanshahi, Kritika Chhabra, Mucahit Cevik, Ayşe Başar
In software engineering practice, fixing a bug promptly reduces the associated costs.
no code implementations • 24 Apr 2021 • Hadi Jahanshahi, Aysun Bozanta, Mucahit Cevik, Eray Mert Kavuk, Ayşe Tosun, Sibel B. Sonuc, Bilgin Kosucu, Ayşe Başar
We consider a meal delivery service fulfilling dynamic customer requests given a set of couriers over the course of a day.
1 code implementation • 24 Apr 2021 • Hadi Jahanshahi, Mucahit Cevik, Ayşe Başar
We observe that LSTM is effective when considering long-run predictions whereas Random Forest Regressor enriched by exogenous variables performs better for predicting the number of bugs in the short term.
1 code implementation • 5 Mar 2021 • Hadi Jahanshahi, Dhanya Jothimani, Ayşe Başar, Mucahit Cevik
In this work, we aim to investigate the effect of code change properties on JIT models over time.
no code implementations • 5 Mar 2021 • Hadi Jahanshahi, Mucahit Cevik, Ayşe Başar
Our main goal is to extend prior research and explore the feasibility of HDP and finally to compare its performance with that of its predecessor, Cross-Project Defect Prediction.