LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints

2026-03-04

AI Summary

This work addresses the challenge that mobile application users often provide vague and unactionable UI feedback, which developers struggle to utilize effectively. To bridge this gap, the authors propose LikeThis!, a novel generative AI–driven interaction paradigm that guides users from expressing complaints toward formulating concrete design suggestions. By jointly analyzing user-provided text comments and screenshots, a multimodal model (e.g., GPT-Image-1) first generates precise improvement specifications and then synthesizes high-fidelity UI design alternatives for user validation. Trained on a newly curated dataset of UI critiques, the approach significantly outperforms existing image generation models. User studies demonstrate that the generated suggestions are more comprehensible and actionable, thereby enhancing collaboration efficiency between users and developers.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

User feedback is crucial for the evolution of mobile apps. However, research suggests that users tend to submit uninformative, vague, or destructive feedback. Unlike recent AI4SE approaches that focus on generating code and other development artifacts, our work aims at empowering users to submit better and more constructive UI feedback with concrete suggestions on how to improve the app. We propose LikeThis!, a GenAI-based approach that takes a user comment with the corresponding screenshot to immediately generate multiple improvement alternatives, from which the user can easily choose their preferred option. To evaluate LikeThis!, we first conducted a model benchmarking study based on a public dataset of carefully critiqued UI designs. The results show that GPT-Image-1 significantly outperformed three other state-of-the-art image generation models in improving the designs to address UI issues while keeping the fidelity and without introducing new issues. An intermediate step in LikeThis! is to generate a solution specification before sketching the design as a key to achieving effective improvement. Second, we conducted a user study with 10 production apps, where 15 users used LikeThis! to submit their feedback on encountered issues. Later, the developers of the apps assessed the understandability and actionability of the feedback with and without generated improvements. The results show that our approach helps generate better feedback from both user and developer perspectives, paving the way for AI-assisted user-developer collaboration.

Problem

• user feedback
• UI improvement
• constructive suggestions
• mobile apps
• developer collaboration

Innovation

• Generative AI
• UI feedback
• solution specification
• user-developer collaboration
• design improvement