Extraction and classification of Non-Functional Requirements from Text Files: A Supervised Learning Approach

Abstract

Non-functional requirements play a critical role in choosing various alternative model and ultimate implementation criteria. It is extremely significant in the earlier stages of software development that requirement engineering produces successful technology and eliminates system failure. The recent work has shown that the automated extraction and classification of quality attributes from text files have been demonstrated by artificial intelligence approaches including machine learning and text mining. In the automated extraction and classification of non-functional specifications, we suggest a supervised categorization approach. To test our approach to obtain interesting outcomes, a very well-known dataset is used. In terms of security and performance, we obtained a specific range of 85% to 98% and obtained a best result together for security, performance and usability.