What Users Value and Critique: Large-Scale Analysis of User Feedback on AI-Powered Mobile Apps

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chhetri, Vinaik, Upadhyay, Krishna, Siddique, A. B., Farooq, Umar
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908405929607168
author Chhetri, Vinaik
Upadhyay, Krishna
Siddique, A. B.
Farooq, Umar
author_facet Chhetri, Vinaik
Upadhyay, Krishna
Siddique, A. B.
Farooq, Umar
contents Artificial Intelligence (AI)-powered features have rapidly proliferated across mobile apps in various domains, including productivity, education, entertainment, and creativity. However, how users perceive, evaluate, and critique these AI features remains largely unexplored, primarily due to the overwhelming volume of user feedback. In this work, we present the first comprehensive, large-scale study of user feedback on AI-powered mobile apps, leveraging a curated dataset of 292 AI-driven apps across 14 categories with 894K AI-specific reviews from Google Play. We develop and validate a multi-stage analysis pipeline that begins with a human-labeled benchmark and systematically evaluates large language models (LLMs) and prompting strategies. Each stage, including review classification, aspect-sentiment extraction, and clustering, is validated for accuracy and consistency. Our pipeline enables scalable, high-precision analysis of user feedback, extracting over one million aspect-sentiment pairs clustered into 18 positive and 15 negative user topics. Our analysis reveals that users consistently focus on a narrow set of themes: positive comments emphasize productivity, reliability, and personalized assistance, while negative feedback highlights technical failures (e.g., scanning and recognition), pricing concerns, and limitations in language support. Our pipeline surfaces both satisfaction with one feature and frustration with another within the same review. These fine-grained, co-occurring sentiments are often missed by traditional approaches that treat positive and negative feedback in isolation or rely on coarse-grained analysis. To this end, our approach provides a more faithful reflection of the real-world user experiences with AI-powered apps. Category-aware analysis further uncovers both universal drivers of satisfaction and domain-specific frustrations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle What Users Value and Critique: Large-Scale Analysis of User Feedback on AI-Powered Mobile Apps
Chhetri, Vinaik
Upadhyay, Krishna
Siddique, A. B.
Farooq, Umar
Software Engineering
Artificial Intelligence
Artificial Intelligence (AI)-powered features have rapidly proliferated across mobile apps in various domains, including productivity, education, entertainment, and creativity. However, how users perceive, evaluate, and critique these AI features remains largely unexplored, primarily due to the overwhelming volume of user feedback. In this work, we present the first comprehensive, large-scale study of user feedback on AI-powered mobile apps, leveraging a curated dataset of 292 AI-driven apps across 14 categories with 894K AI-specific reviews from Google Play. We develop and validate a multi-stage analysis pipeline that begins with a human-labeled benchmark and systematically evaluates large language models (LLMs) and prompting strategies. Each stage, including review classification, aspect-sentiment extraction, and clustering, is validated for accuracy and consistency. Our pipeline enables scalable, high-precision analysis of user feedback, extracting over one million aspect-sentiment pairs clustered into 18 positive and 15 negative user topics. Our analysis reveals that users consistently focus on a narrow set of themes: positive comments emphasize productivity, reliability, and personalized assistance, while negative feedback highlights technical failures (e.g., scanning and recognition), pricing concerns, and limitations in language support. Our pipeline surfaces both satisfaction with one feature and frustration with another within the same review. These fine-grained, co-occurring sentiments are often missed by traditional approaches that treat positive and negative feedback in isolation or rely on coarse-grained analysis. To this end, our approach provides a more faithful reflection of the real-world user experiences with AI-powered apps. Category-aware analysis further uncovers both universal drivers of satisfaction and domain-specific frustrations.
title What Users Value and Critique: Large-Scale Analysis of User Feedback on AI-Powered Mobile Apps
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2506.10785