Patterns for Identifying and Structuring Features from Textual Descriptions: An Exploratory Study

Software Product Line Engineering (SPLE) supports developing and managing families of similar software products, termed Software Product Lines (SPLs). An essential SPLE activity is variability modeling which aims at representing the differences among the SPL’s members. This is commonly done with feature diagrams – graph structures specifying the user visible characteristics of SPL’s members and the dependencies among them. Despite the attention that feature diagrams attract, the identification of features and structuring them into feature diagrams remain challenging. In this study, we utilized Natural Language Processing (NLP) techniques in order to explore different patterns for identifying and structuring features from textual descriptions. Such a catalog of patterns is important for both manually-created and automatically-generated feature diagrams.

• Type: Journal
• Year: 2015
• Where: CAISE
• Authors: Nili Itzik, Iris Reinhartz-Berger
• Keywords: CAISE 2015, Information Technology