by Saad Shafiq, Atif Mashkoor, Christoph Mayr-Dorn, Alexander Egyed
Abstract:
This paper proposes a recommendation approach for issues (e.g., a story, a bug, or a task) prioritization based on natural language processing, called NLP4IP. The proposed semi-automatic approach takes into account the priority and story points attributes of existing issues defined by the project stakeholders and devises a recommendation model capable of dynamically predicting the rank of newly added or modified issues. NLP4IP was evaluated on 19 projects from 6 repositories employing the JIRA issue tracking software with a total of 29,698 issues. A comprehensive benchmark study was also conducted to compare the performance of various machine learning models. The results of the study showed an average top@3 accuracy of 81% and a mean squared error of 2.2 when evaluated on the validation set. The applicability of the proposed approach is demonstrated in the form of a JIRA plug-in illustrating predictions made by the newly developed machine learning model. The dataset has also been made publicly available in order to support other researchers working in this domain.
Reference:
NLP4IP: Natural Language Processing-based Recommendation Approach for Issues Prioritization (Saad Shafiq, Atif Mashkoor, Christoph Mayr-Dorn, Alexander Egyed), In 47th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2021, Palermo, Italy, September 1-3, 2021 (Maria Teresa Baldassarre, Giuseppe Scanniello, Amund Skavhaug, eds.), IEEE, 2021.
Bibtex Entry:
@Conference{Shafiq2021a,
author = {Saad Shafiq and Atif Mashkoor and Christoph Mayr-Dorn and Alexander Egyed},
booktitle = {47th Euromicro Conference on Software Engineering and Advanced Applications, {SEAA} 2021, Palermo, Italy, September 1-3, 2021},
title = {{NLP4IP:} Natural Language Processing-based Recommendation Approach for Issues Prioritization},
year = {2021},
editor = {Maria Teresa Baldassarre and Giuseppe Scanniello and Amund Skavhaug},
pages = {99--108},
publisher = {{IEEE}},
abstract = {This paper proposes a recommendation approach for issues (e.g., a story, a bug, or a task) prioritization based on natural language processing, called NLP4IP. The proposed semi-automatic approach takes into account the priority and story points attributes of existing issues defined by the project stakeholders and devises a recommendation model capable of dynamically predicting the rank of newly added or modified issues. NLP4IP was evaluated on 19 projects from 6 repositories employing the JIRA issue tracking software with a total of 29,698 issues. A comprehensive benchmark study was also conducted to compare the performance of various machine learning models. The results of the study showed an average top@3 accuracy of 81% and a mean squared error of 2.2 when evaluated on the validation set. The applicability of the proposed approach is demonstrated in the form of a JIRA plug-in illustrating predictions made by the newly developed machine learning model. The dataset has also been made publicly available in order to support other researchers working in this domain.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/conf/euromicro/ShafiqMME21.bib},
doi = {10.1109/SEAA53835.2021.00022},
file = {:Conferences/SEAA 2021 - NLP4IP Natural Language Processing-based Recommendation Approach for Issues Prioritization/NLP4IP Natural Language Processing-based Recommendation Approach for Issues Prioritization - preprint.pdf:PDF},
keywords = {LIT AI Lab, LIT Secure and Correct Systems Lab},
timestamp = {Fri, 29 Oct 2021 16:42:35 +0200},
url = {https://doi.org/10.1109/SEAA53835.2021.00022},
}