User Modeling and User Profiling: A Comprehensive Survey

TL;DR

This survey provides a comprehensive historical view and formal taxonomy of user modeling and profiling, tracing from stereotype-based beginnings to modern deep-learning and graph-based approaches. It synthesizes implicit, explicit, and hybrid data collection, diverse representation schemes, and a broad spectrum of modeling techniques, while foregrounding beyond-accuracy concerns such as explainability, fairness, and privacy. The authors introduce encyclopedic definitions for core terms and discuss paradigm shifts toward universal and holistic user representations, graph-structured data, and cross-domain applications. The work highlights emergent directions including Human-AI collaboration, cognitive-science integration, and responsible AI, positioning user modeling as central to ethically personalized, effective AI systems in domains like fake news detection, cybersecurity, and adaptive education.

Abstract

The integration of artificial intelligence (AI) into daily life, particularly through information retrieval and recommender systems, has necessitated advanced user modeling and profiling techniques to deliver personalized experiences. These techniques aim to construct accurate user representations based on the rich amounts of data generated through interactions with these systems. This paper presents a comprehensive survey of the current state, evolution, and future directions of user modeling and profiling research. We provide a historical overview, tracing the development from early stereotype models to the latest deep learning techniques, and propose a novel taxonomy that encompasses all active topics in this research area, including recent trends. Our survey highlights the paradigm shifts towards more sophisticated user profiling methods, emphasizing implicit data collection, multi-behavior modeling, and the integration of graph data structures. We also address the critical need for privacy-preserving techniques and the push towards explainability and fairness in user modeling approaches. By examining the definitions of core terminology, we aim to clarify ambiguities and foster a clearer understanding of the field by proposing two novel encyclopedic definitions of the main terms. Furthermore, we explore the application of user modeling in various domains, such as fake news detection, cybersecurity, and personalized education. This survey serves as a comprehensive resource for researchers and practitioners, offering insights into the evolution of user modeling and profiling and guiding the development of more personalized, ethical, and effective AI systems.

Figures (3)

• Figure 1: Timeline reporting the major events of the user modeling and profiling history.
• Figure 2: Taxonomy of the reviewed literature and trends for user modeling. The Modeling techniques tree is detailed in Figure \ref{['fig:modeling_techniques']}.
• Figure 3: Specific taxonomy of the Modeling techniques.