Semi-Supervised Classification of Non-Functional Requirements: An Empirical Analysis
Agustin Casamayor, Daniela Godoy, Marcelo Campo · INTELIGENCIA ARTIFICIAL · 2010
"The early detection and classication of non-functional requirements (NFRs) is not only a hard and time consuming process, but also crucial in the evaluation of architectural alternatives starting from initial design decisions. In this paper, we propose a recommender system based on a semi-supervised learning approach for assisting analysts in the detection and classication of NFRs from textual requirements descriptions. Classica- tion relies on a reduced number of categorized requirements and takes advantage of the knowledge provided by uncategorized ones as well as certain properties of text. Experimental results show that the proposed recommen- dation approach based on semi-supervised learning outperforms previous proposals for classifying di?erent types of requirements."