Mining User Requirements from Application Store Reviews Using Frame Semantics

Mining user requirements from application store reviews using frame semantics N. Jha and A. Mahmoud, Requirements Engineering: Foundation for Software Quality (REFSQ), accepted, 2017 Papers Research on mining user reviews in mobile application stores has noticeably advanced in the past few years. The majority of the proposed techniques rely on classifying the textual description of user reviews into different categories of technically informative user requirements and uninformative feedback. Relying on the textual attributes of reviews, however, often produces high dimensional models. This increases the complexity of the classifier and can lead to overfitting problems. We propose a novel approach for application review classification. The proposed approach is based on the notion of semantic role labeling, or characterizing the lexical meaning of text in terms of semantic frames. Semantic frames help to generalize from text (individual words) to more abstract scenarios (contexts). This reduces the dimensionality of the data and enhances the predictive capabilities of the classifier. As a result, the proposed approach can be used to generate lower dimensional and more accurate models in comparison to text classification methods. Abstract