The 1st Workshop on Human-Centered Recommender Systems (HCRS) at TheWebConf 2025 offers a unique platform to discuss and advance the development of recommender systems that prioritize human needs, values, and capabilities. We welcome research papers that explore ethical, social, technical, and user-oriented challenges in building responsible and human-centered recommender systems.

We encourage in-person participation, but remote presentation will be available for authors who cannot travel to Sydney.

Topics of Interest

The HCRS workshop seeks to address diverse challenges in creating recommender systems that are not only effective but also ethical, trustworthy, and user-friendly. Topics include (but are not limited to):

  • Robustness: Fraud detection, adversarial defenses, vulnerabilities of LLM-based recommender systems, user-aware robustness, and more.
  • Privacy: Differential privacy, federated learning, data ownership, privacy risks in LLM-based RS, unlearning, and related areas.
  • Transparency: Explainable and interpretable recommender systems, causal explanations, and transparency enhancements using LLMs.
  • Fairness and Bias: Addressing and debiasing algorithmic biases, fairness in LLM-based RS, and fairness evaluation frameworks.
  • Diversity: Content diversity, addressing filter bubbles and echo chambers, and balancing personalization with diverse recommendations.
  • Ethics: Ethical frameworks, user consent, responsible data usage, and mitigating misinformation in recommender systems.
  • Accountability: Traceability, responsible recommendations, and controllable or auditable algorithms.
  • Human-Computer Interaction Design: User-centric interfaces, conversational and interactive recommender systems, and accessibility.
  • Evaluation and Auditing: Innovative evaluation metrics, user satisfaction studies, auditing algorithms for biases, and governance frameworks.

We particularly welcome submissions connecting these topics to emerging technologies, such as large language models (LLMs), and their impact on recommender systems.

Submission Guidelines

We invite submissions between 4 and 8 pages (excluding references) covering the above topics. Manuscripts will be reviewed by our program committee through a single-blind review process, meaning that authors’ names do not need to be anonymized. Accepted submissions will be presented either as oral talks or posters during the workshop.

For unpublished work, authors have the option to include their accepted papers in the Companion Proceedings of the Web Conference 2025, provided they meet the camera-ready timeline. Including a paper in the companion proceedings does not restrict future submissions to other venues. Previously published work is also welcome for submission to the workshop, but such work will not be included in the companion proceedings.

This policy encourages open discussions while respecting the integrity of prior and future publications.

Paper Format

All submissions must be in English and must adhere to the ACM template and format (also available in Overleaf), with the following options:

\setcopyright{none}

CCS class and keywords sections are optional.

  • Papers must be between 4 and 8 pages in the ACM manuscript format (excluding references).
  • Appendices are allowed but will not count toward the page limit. References and acknowledgements are excluded from the page count.

Submission

Papers should be submitted from Openreview.

Important Dates

  • 2025-01-06: Paper submission deadline
  • 2025-01-20: Author notification
  • 2025-02-02: Camera-ready submission
  • 2025-04-28: Workshop (half-day session)

TIMEZONE: Anywhere On Earth (UTC-12)

We look forward to your contributions and to fostering discussions on creating ethical, user-friendly, and socially responsible recommender systems!