Full Program »
Multi-label Classifier to Deal with Miss-Classification in NFRs
Automatic classification of software requirements is an active research area, it can alleviate the tedious task of manual labelling and improves transparency in the requirements engineering process. Several attempts have been made to contribute to the identification and classification of Functional requirements (FRs) as well as Non-functional requirements (NFRs) by their type. But, previous work in this regard suffers from miss classification. This study investigates the issues with NFRs, in particular: the limitation of the existing methods for NFRs classification;
The goal of this work is to minimize miss-classification and help stakeholder to consider NFRs in early phases of development through automatically classifying requirements.
In this study, we have proposed an improved requirement detection and classification technique. The following summarizes the proposed approach:
(1) A newly created gold standard corpus. (2) Textual semantics to augment user requirements by word2vec for automatically extracting features, and (3) A CNN(Convolution neural network ) based multi-label requirement classifier which classifies NFRs into five classes. (Reliability, Efficiency, Portability, Usability and Maintainability).