Identifying Use Case Elements from Textual Specification: A Preliminary Study
Saurabh Kumar Tiwari, Santosh Singh Rathore, Shreya Sagar, Yash Mirani · 2020
Software requirements are described in some form of natural language (NL) text so that stakeholders with limited experience can also comprehend them easily. However, the NL text written document is inherently ambiguous, and this makes it hard to examine requirements manually to find inconsistencies, duplicates, and/or missing requirements. Use Case Analysis is a graphical depiction used to explain the interaction between the user and the system for the given user's task. Additionally, it denotes the extension/dependency of one use case to another to understand the system flow. It is often used to identify, clarify, and categorize system requirements. However, generating use cases from a textual written description of requirements is an arduous task involving a significant manual work, which can be automated using data-driven techniques. In this poster paper, we present an initial approach for the automated identification of use case names and actor names from the textual requirements specification using machine learning techniques.