Aprendizado de máquina na melhoria da experiência do usuário em interfaces digitais web e mobile: uma revisão sistemática

Abstract

The creation of digital interfaces that meet users expectations remains a challenge, as many systems still feature complex and difficult-to-use designs. In this context, machine learning emerges as a promising solution, allowing systems to adjust to users preferences and needs. The goal of this work is to conduct a systematic literature review on the application of machine learning algorithms to improve the user experience in web and mobile digital interfaces. The methodology adopted was the systematic literature review, with research based on articles published between 2021 and 2024, collected from IEEE Xplore, Web of Science, and Scopus. The selection of studies was carried out in two phases, with the application of inclusion and exclusion criteria. The results indicated that machine learning positively impacts the personalization of interfaces, using techniques such as behavior analysis, eye-tracking, and user segmentation. Additionally, performance metrics such as success rate, interaction time, and accuracy are essential for validating improvements. The study concludes that machine learning contributes to the creation of more intuitive interfaces aligned with users expectations. The identified research gaps highlight the need for future investigations into mitigating cognitive overload and utilizing multimodal assistants to develop even more adaptable and accessible interfaces.