Automating App Review Response Generation Based on Contextual Knowledge
This work addresses the challenge of automating review responses for app developers to improve user experience, but it is incremental as it builds on prior methods by enhancing contextual integration.
The paper tackles the problem of generating high-quality responses to mobile app reviews by proposing CoRe, an end-to-end neural network that incorporates contextual knowledge from app descriptions and similar reviews, resulting in an 11.53% improvement in BLEU-4 score over the state-of-the-art method.
User experience of mobile apps is an essential ingredient that can influence the audience volumes and app revenue. To ensure good user experience and assist app development, several prior studies resort to analysis of app reviews, a type of app repository that directly reflects user opinions about the apps. Accurately responding to the app reviews is one of the ways to relieve user concerns and thus improve user experience. However, the response quality of the existing method relies on the pre-extracted features from other tools, including manually-labelled keywords and predicted review sentiment, which may hinder the generalizability and flexibility of the method. In this paper, we propose a novel end-to-end neural network approach, named CoRe, with the contextual knowledge naturally incorporated and without involving external tools. Specifically, CoRe integrates two types of contextual knowledge in the training corpus, including official app descriptions from app store and responses of the retrieved semantically similar reviews, for enhancing the relevance and accuracy of the generated review responses. Experiments on practical review data show that CoRe can outperform the state-of-the-art method by 11.53% in terms of BLEU-4, an accuracy metric that is widely used to evaluate text generation systems.