Implementation of Machine Learning Based Microinteractions to Improve User Experience in Hospital Mobile Applications

The development of hospital mobile applications requires improving the quality of User Experience (UX) that is not only oriented towards functional aspects, but also the emotional dimension of users. This study aims to explore the application of microinteractions based on a machine learning perspective to improve UX in hospital mobile applications. The research approach uses a quantitative method with the User Experience Questionnaire (UEQ) instrument to measure pragmatic and hedonic qualities after the implementation of microinteractions on an application prototype developed using Figma. The testing process involved 14 randomly selected respondents and analyzed using the Data Analysis Tool (UEQ-S). The results showed a Pragmatic Quality score of 2.375, a Hedonic Quality score of 2.268, and an overall score of 2.321, indicating that the implementation of microinteractions provided a positive user experience but still has room for development. From a machine learning-based analytics perspective, the obtained UX data can be viewed as a numerical representation of user perception patterns that can potentially be further analyzed using clustering or predictive techniques to identify preferences and the contribution of each dimension to user satisfaction. Although the machine learning model was not directly implemented in the system, this study demonstrates that microinteractions can serve as interaction data points that support the development of adaptive systems based on data learning in the future. Thus, this study not only confirms the effectiveness of microinteractions in improving UX functionally and emotionally, but also opens up opportunities for the integration of intelligent analytics to create more responsive, personalized, and data-driven hospital mobile applications.

Keywords: microinteraction, machine learning, user experience, hospital mobile applications, UEQ