University of Twente Student Theses

Login
This website will be unavailable due to maintenance December 1st between 8:00 and 12:00 CET.

Using augmented software requirements for automatic classification

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

[img] PDF
861kB
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:https://purl.utwente.nl/essays/91699
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page