Klasifikasi Kebutuhan Non-Fungsional Menggunakan Fsknn Dengan Pengembangan Sinonim Dan Hipernin Berbasis ISO/IEC 9126

Abstract

Non-functional requirements is one of the important factors that play a role in the success of software development that is often forgotten by the developer, causing adverse effects. To obtain the non-functional requirements needed an automation system identification non-functional requirements. In this study proposed an an automation system of identification of non-functional requirements from the requirement sentences based classification algorithms FSKNN with term enrichment on training data using synonyms and combined hypernym and synonyms based on ISO / IEC 9126. In the testing phase the dataset of requirement sentence used was 1342 sentences from six different datasets Results of this research is the term enrichment by using a combination hypernym and synonyms can improve performance accuracy by 8.1%, precision by 13% and a recall by 4.9%.