User Modeling in Model-Driven Engineering: A Systematic Literature Review

TL;DR

This paper systematically reviews user modeling in model-driven engineering, highlighting its fragmented state and advocating for richer, integrated user models to enhance personalized, adaptive software interfaces, especially with AI advancements.

Contribution

It provides a comprehensive analysis of existing user modeling approaches in MDE, identifying gaps and advocating for unified, richer models to improve personalization.

Findings

Lack of unified user modeling perspective in MDE

Most proposals consider only simple user dimensions

Limited tool support for comprehensive user models

Abstract

In software applications, user models can be used to specify the profile of the typical users of the application, including personality traits, preferences, skills, etc. In theory, this would enable an adaptive application behavior that could lead to a better user experience. Nevertheless, user models do not seem to be part of standard modeling languages nor common in current model-driven engineering (MDE) approaches. In this paper, we conduct a systematic literature review to analyze existing proposals for user modeling in MDE and identify their limitations. The results showcase that there is a lack of a unified and complete user modeling perspective. Instead, we observe a lot of fragmented and partial proposals considering only simple user dimensions and with lack of proper tool support. This limits the implementation of richer user interfaces able to better support the user-specific needs. Therefore, we hope this analysis triggers a discussion on the importance of user models and their inclusion in MDE pipelines. Especially in a context where, thanks to the rise of AI techniques, personalization, based on a rich number of user dimensions, is becoming more and more of a possibility.