Listening to Users' Voice: Automatic Summarization of Helpful App Reviews

App reviews are crowdsourcing knowledge of user experience with the apps, providing valuable information for app release planning, such as major bugs to fix and important features add. There exist prior explorations on review mining planning; however, most studies strongly rely predefined classes or manually annotated reviews. Also, new characteristic, i.e., number users who rated helpful, which can help capture reviews, has not been considered previously. In article, we propose a novel framework, named SOLAR, aiming at accurately summarizing helpful developers. The framework mainly contains three modules: helpfulness prediction module, topic-sentiment modeling multifactor ranking module. module assesses whether is useful groups topics also predicts associated sentiment, aims prioritizing semantically representative each topic summary. Experiments five popular apps indicate that SOLAR effective summarization promising facilitating planning.