# App-Aware Response Synthesis for User Reviews

arXiv: https://arxiv.org/abs/2007.15793 · HTML: https://mlsanity.com/paper/2007.15793/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [Generalized Zero-shot Intent Detection via Commonsense Knowledge](https://mlsanity.com/paper/2102.02925/) (2021)
- [Linguistically-Enriched and Context-Aware Zero-shot Slot Filling](https://mlsanity.com/paper/2101.06514/) (2021)
- [MobileRec: A Large-Scale Dataset for Mobile Apps Recommendation](https://mlsanity.com/paper/2303.06588/) (2023)
- [Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function](https://mlsanity.com/paper/2303.13797/) (2023)
- [Self-Improving Customer Review Response Generation Based on LLMs](https://mlsanity.com/paper/2405.03845/) (2024)
- [Proactive Prioritization of App Issues via Contrastive Learning](https://mlsanity.com/paper/2303.06586/) (2023)
- [Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generation](https://mlsanity.com/paper/2202.02294/) (2022)
- [MobileConvRec: A Conversational Dataset for Mobile Apps Recommendations](https://mlsanity.com/paper/2405.17740/) (2024)
- [What Users Value and Critique: Large-Scale Analysis of User Feedback on AI-Powered Mobile Apps](https://mlsanity.com/paper/2506.10785/) (2025)
- [INTERPOS: Interaction Rhythm Guided Positional Morphing for Mobile App Recommender Systems](https://mlsanity.com/paper/2506.12661/) (2025)

## Abstract (arXiv)

Responding to user reviews promptly and satisfactorily improves application ratings, which is key to application popularity and success. The proliferation of such reviews makes it virtually impossible for developers to keep up with responding manually. To address this challenge, recent work has shown the possibility of automatic response generation. However, because the training review-response pairs are aggregated from many different apps, it remains challenging for such models to generate app-specific responses, which, on the other hand, are often desirable as apps have different features and concerns. Solving the challenge by simply building a model per app (i.e., training with review-response pairs of a single app) may be insufficient because individual apps have limited review-response pairs, and such pairs typically lack the relevant information needed to respond to a new review. To enable app-specific response generation, this work proposes AARSynth: an app-aware response synthesis system. The key idea behind AARSynth is to augment the seq2seq model with information specific to a given app. Given a new user review, it first retrieves the top-K most relevant app reviews and the most relevant snippet from the app description. The retrieved information and the new user review are then fed into a fused machine learning model that integrates the seq2seq model with a machine reading comprehension model. The latter helps digest the retrieved reviews and app description. Finally, the fused model generates a response that is customized to the given app. We evaluated AARSynth using a large corpus of reviews and responses from Google Play. The results show that AARSynth outperforms the state-of-the-art system by 22.2% on BLEU-4 score. Furthermore, our human study shows that AARSynth produces a statistically significant improvement in response quality compared to the state-of-the-art system.