PofoliaShared via Pofolia

International Journal of Human-Computer Interaction· 2026Q1

mUXSmellDetection: An LLM-Assisted Framework for Automated UX Smell Detection in Mobile Apps

Haifa Al‐Shammare, Mohammad Alshayeb, Malak Baslyman

Short summary

A new framework, mUXSmellDetection, uses LLMs (GPT-5 achieved 91.67% F1-score) to automatically detect 40 standardized UX smells in Android apps by analyzing runtime logs, screenshots, and code metadata.

AI-generated from the title and abstract; the full text is not read.

Key points

  • mUXSmellDetection is a catalog-driven, multi-modal framework for automated UX smell detection in Android apps.
  • It utilizes a catalog of 40 standardized UX smells with defined detection rules.
  • The framework integrates runtime logs, GUI screenshots, and Java AST code metadata.
  • LLMs (GPT-4o, GPT-5, GPT-5 Thinking) were used for detection, with GPT-5 achieving 94.29% Precision, 89.19% Recall, and 91.67% F1-score against expert baselines.
  • Multi-modal evidence integration enables scalable and practical automated UX smell detection.

AI-generated from the title and abstract; the full text is not read.

Abstract

Mobile applications increasingly support critical services, making high-quality user experience (UX) essential. Nevertheless, scalable UX evaluation remains challenging because it relies on expert judgment and heterogeneous evidence. This study introduces mUXSmellDetection, a catalog-driven, multi-modal framework for automated UX smell detection in Java-based Android applications. A Mobile UX Smells Catalog was developed, comprising 40 standardized UX smells with explicit detection rules and evidence requirements. The framework integrates runtime interaction logs collected through hybrid in-app and system-level logging, GUI screenshots, and Java AST-based code metadata, which are transformed into structured prompts for large language models (LLMs). The approach was evaluated on ten real-world Android applications using GPT-4o, GPT-5, and GPT-5 Thinking. Detection results were compared to an expert baseline established by three UX experts. GPT-5 achieved the highest overall performance, with 94.29% Precision, 89.19% Recall, and 91.67% F1-score. These findings indicate that multi-modal evidence enables scalable and practical automated UX smell detection.

The authors' abstract, as published at the source. International Journal of Human-Computer Interaction, 2026 · DOI ↗

TakeawaysIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Computer Science Applications

Computer Science ApplicationsComputer Science