Reproduce “User Modeling and User Profiling: A Comprehensive Survey” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Erasmo Purificato, Ludovico Boratto, Ernesto William De Luca

This comprehensive survey maps the historical evolution of user modeling and profiling, proposing a new taxonomy to organize the field while clarifying ambiguous terminology. It synthesizes recent advancements, highlighting the integration of deep learning, graph structures, and an increasing focus on ethical considerations like privacy, fairness, and explainability in user model development.

Key insights

  • User modeling has evolved from stereotype-based methods to sophisticated deep learning and graph-based approaches, increasingly incorporating ethical considerations.
  • The paper provides a structured framework through a novel taxonomy that organizes the diverse research topics, methods, and applications within user modeling and profiling.
  • There is a growing imperative to integrate 'beyond-accuracy' perspectives such as privacy, fairness, and explainability into user model development.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.