University of Twente Student Theses


Using augmented software requirements for automatic classification

Copae, D.V. (2022) Using augmented software requirements for automatic classification.

[img] PDF
Abstract:The recent growth in the number and complexity of software applications is producing an increasing need for high-quality software requirements. Manual classification of requirements can be a cumbersome and tedious process, which leads to leveraging Machine Learning and Natural Language Processing techniques for automated classification. This paper explores the effects of augmenting a software requirement dataset with synonymous words by using the word2vec word embedding technique and diverse feature extraction and classification methods. The experiment results show that the proposed augmentation technique improves the F1-score when using the Multinomial Naive Bayes and Logistic Regression classifiers by 0.57% and 0.88% respectively.
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:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page