The signifcance of user satisfaction is increasing in the competitive open source software (OSS) market. Application stores let users send their feedbacks for applications, which are in the form of user reviews or ratings. Developers are informed about bugs or any additional requirements with the help of this feedback and use it to increase the quality of the software. Moreover, potential users rely on this information as a success indicator to decide downloading the applications. Since it is usually costly to read all the reviews and evaluate their content, the ratings are taken as the base for the assessment. This makes the consistency of the contents with the ratings of the reviews important for healthy evaluation of the applications. In this study, we use recurrent neural networks to analyze the reviews automatically, and thereby predict the user ratings based on the reviews. We apply transfer learning from a huge volume, gold dataset of Amazon Customer Reviews. We evaluate the performance of our model on three mobile OSS applications in the Google Play Store and compare the predicted ratings and the original ratings of the users. Eventually, the predicted ratings have an accuracy of 87.61% compared to the original ratings of the users, which seems promising to obtain the ratings from the reviews especially if the former is absent or its consistency with the reviews is weak.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.