Traditional user research methods are challenged for the decision-making in product design and improvement with the updating speed becoming faster, considering limited survey scopes, insufficient samples, and time-consuming processes. This paper proposes a novel approach to acquire useful online reviews from E-commerce platforms, build a product evaluation indicator system, and put forward improvement strategies for the product with opinion mining and sentiment analysis with online reviews. The effectiveness of the method is validated by a large number of user reviews for smartphones wherein, with the evaluation indicator system, we can accurately predict the bad review rate for the product with only 9.9% error. And improvement strategies are proposed after processing the whole approach in the case study. The approach can be applied for product evaluation and improvement, especially for the products with needs for iterative design and sailed online with plenty of user reviews.
7 January 2021 in Computer-Aided Design and Applications
Mobile application (app) reviews are feedback about experiences, requirements, and issues raised after users have used the app. The iteration of an app is driven by bug reports and user requirements analyzed and extracted from app reviews, which is a problem that app designers and developers are committed to solving. However, a great number of app reviews vary in quality and reliability. It is a difficult and time-consuming challenge to analyze app reviews using manual methods. To address this, a novel approach is proposed as an automated method to predict high priority user requests with fourteen extracted features. A semi-automated approach is applied to annotate requirements with high or low priority with the help of app changelogs. Reviews from six apps were retrieved from the Apple App Store to evaluate the feasibility of the approach and interpret the principles. The performance comparison results of the approach greatly exceed the IDEA method, with an average precision of 75.4% and recall of 70.4%. Our approach can be applied to specific app development to assist app developers in quickly locating user requirements and implement app maintenance and evolution.