Institutional Repository of Vilnius University
Nefunkcinių reikalavimų klasifikavimo modelis pagal ISO/IEC 25010 standartą /
Abstract
dc:descriptionNon-functional requirements can be misclassified for a variety of reasons, which can adversely affect the quality of the software. To address this problem, this thesis aims to develop algorithm that is able to correctly classify non-functional requirements according to the quality characteristics listed in ISO/IEC 25010 standard. Classification was carried out using different machine learning and natural language processing algorithms. Parameter tuning of the classification algorithms was carried out in an attempt to obtain maximum accuracy of the model. The analysis of the results shows that algorithm and parameter selection have the greatest impact on the accuracy of the classification model. The best results were obtained using support vector machine and naive Bayes algorithms. The performance of the natural language processing methods depended on the machine learning algorithm used. The highest recorded accuracy is 71%.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kančys, Henrikas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192842476&prefLang=en_US