REVIEW 4 minor 19 references
The 1st Workshop on Human-Centered Recommender Systems
T0 review · 0 major / 4 minor · reviewed 2026-08-12 · deepseek-v4-flash
Pith's one-line read This workshop proposal makes the case that recommender systems should be designed and evaluated around human needs, values, and capabilities, and it lays out a half-day program to consolidate that research community.
desk verdict A straightforward workshop proposal with no scientific claims; harmless, honest, and not something a referee needs to spend time on. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The carrying object is the concept of HCRS itself, defined as recommender systems that put human needs, values, and capabilities at the core of their design and operation. The definitional contrast with Trustworthy Recommender Systems and Responsible Recommender Systems does the work of marking out a distinct territory for the field. The proposed workshop program, with two keynote talks, two paper sessions, a panel discussion, and 8-10 accepted papers, is the mechanism for turning that conceptual territory into an ongoing research community.
What would settle it
Check the workshop's final program: if it lists far fewer than the planned 8-10 papers or drops the panel, the paper's premise that the community is ready for a dedicated human-centered recommender systems venue would be contradicted.
Extended reading notes
Core claim
The paper's central claim is that human-centered recommender systems are a distinct and active research direction that deserves its own dedicated venue. HCRS means building recommenders that prioritize human needs, values, and capabilities at the core of their design and operation, and it actively involves users through methods such as participatory design and user studies. The paper contrasts this with Trustworthy Recommender Systems, which emphasize reliability and transparency, and Responsible Recommender Systems, which emphasize ethical alignment and social responsibility. The proposed half-day workshop is the vehicle for consolidating this community and advancing an agenda centered on user well-being, satisfaction, and empowerment.
Load-bearing premise
The load-bearing premise is that enough researchers will submit papers and attend so that the planned 8-10 accepted papers, two keynotes, and panel discussion can actually take place; without that community response, the workshop cannot deliver its stated objectives.
Editorial extensions
If this is right
- Evaluation of recommender systems would broaden from accuracy to include user satisfaction, trust, autonomy, and well-being.
- Privacy, fairness, transparency, diversity, and accountability would be treated as required design considerations rather than optional extras.
- Participatory design and user studies would become standard methods in recommender-system research instead of edge cases.
- Over the long term, the agenda is expected to push recommender systems into broader domains and align them with societal well-being, as the paper's rationale states.
Reading between the lines
- A consequence the authors do not spell out is that a recurring HCRS workshop could consolidate a shared evaluation suite or benchmark for human-centered properties, since the call for papers emphasizes new metrics and auditing methods.
- If this framing catches hold, HCRS may partially merge with trustworthy and responsible recommender research in practice; the workshop's discussions would be a natural place to test whether these three labels describe different activities or one agenda.
- A testable extension would be to compare the evaluation metrics used in papers presented at this workshop against those used at general recommender-system venues, looking for differences in how often user-reported well-being, control, or trust appears.
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. This manuscript is a workshop proposal for the 1st Workshop on Human-Centered Recommender Systems, to be held at WWW'25. It introduces the concept of HCRS, differentiates it from trustworthy and responsible recommender systems, lists topics of interest (robustness, privacy, transparency, fairness, diversity, ethics, accountability, HCI design, evaluation), gives a rationale and objectives, presents a half-day program schedule, names an intended program committee, and includes a call for papers with deadlines. No technical results, data, or derivations are presented; the paper is an organizational announcement.
Significance. The paper's significance is organizational rather than scientific. If the workshop convenes as planned, it may facilitate discussion and community building around human-centered recommender systems, which is a timely topic. The proposal is clearly written and includes useful concrete elements: a structured program, a list of specific research topics, and transparency about provisional aspects such as not-yet-contacted program committee members. There is no experimental or theoretical claim that can be verified, so the significance rests on the community value of the event itself.
minor comments (4)
- [Header and ACM Reference Format] The copyright line and the ACM Reference Format state '© 2018' and '.2018' while the conference is WWW'25 (April 28–May 2, 2025); these should be corrected to 2025.
- [Header and Table 1] The date 'Apri 28–May 02, 2025' contains a typo; it should be 'April 28–May 2, 2025'.
- [Section 4, Workshop Program Format] In the list of prospective program committee members, 'Cornel University' should be spelled 'Cornell University'.
- [Section 4, Workshop Program Format] The footnote already notes that the schedule is provisional, but the list of individuals 'whom we have not yet contacted' could be labeled more explicitly as 'planned, not yet confirmed' to avoid any impression of commitment.
Circularity Check
No circularity: the paper is a workshop proposal with no derivations, fitted parameters, or predictions whose correctness could reduce to its own inputs.
full rationale
This manuscript is a proposal for the 1st Workshop on Human-Centered Recommender Systems, not a technical research paper. It contains no equations, no fitted parameters, no experimental results, and no predictive claims. The central assertion is organizational: that such a workshop is needed and will facilitate discussion and advance the field. The rationale sections cite prior work, including some by the organizers, but they use those citations only to establish that human-centered recommender systems are an active research area, not as a load-bearing derivation of a result. The practical assumption that enough high-quality submissions and confirmed keynote speakers will materialize is inherent to any workshop proposal and is explicitly flagged as provisional in the footnote to Section 4. Metadata errors such as the 2018 copyright year and the misspelling of 'April' do not constitute circularity. Therefore, the circularity score is 0.
Assumptions & free parameters
Cite this review
Pith. "Pith review of The 1st Workshop on Human-Centered Recommender Systems." pith.science (2026). https://pith.science/paper/AJ7HZ3MT
@misc{pith2026241114760,
author = {Pith},
title = {Pith review of: The 1st Workshop on Human-Centered Recommender Systems},
year = {2026},
howpublished = {\url{https://pith.science/paper/AJ7HZ3MT}},
note = {Machine review of arXiv:2411.14760}
}
read the original abstract
Recommender systems are quintessential applications of human-computer interaction. Widely utilized in daily life, they offer significant convenience but also present numerous challenges, such as the information cocoon effect, privacy concerns, fairness issues, and more. Consequently, this workshop aims to provide a platform for researchers to explore the development of Human-Centered Recommender Systems~(HCRS). HCRS refers to the creation of recommender systems that prioritize human needs, values, and capabilities at the core of their design and operation. In this workshop, topics will include, but are not limited to, robustness, privacy, transparency, fairness, diversity, accountability, ethical considerations, and user-friendly design. We hope to engage in discussions on how to implement and enhance these properties in recommender systems. Additionally, participants will explore diverse evaluation methods, including innovative metrics that capture user satisfaction and trust. This workshop seeks to foster a collaborative environment for researchers to share insights and advance the field toward more ethical, user-centric, and socially responsible recommender systems.
Reference graph
Works this paper leans on
-
[1]
Giacomo Balloccu, Ludovico Boratto, Gianni Fenu, Francesca Maridina Malloci, and Mirko Marras. 2024. Explainable Recommender Systems with Knowledge Graphs and Language Models. In European Conference on Information Retrieval . Springer, 352–357
work page 2024
-
[2]
Yashar Deldjoo, Dietmar Jannach, Alejandro Bellogin, Alessandro Difonzo, and Dario Zanzonelli. 2024. Fairness in Recommender Systems: Research Landscape and Future Directions. User Modeling and User-Adapted Interaction 34, 1 (2024), 59–108
2024
-
[3]
Yingqiang Ge, Shuchang Liu, Zuohui Fu, Juntao Tan, Zelong Li, Shuyuan Xu, Yunqi Li, Yikun Xian, and Yongfeng Zhang. 2022. A Survey on Trustworthy Recommender Systems. ACM Transactions on Recommender Systems (2022)
work page 2022
-
[4]
Przemysław Kazienko and Erik Cambria. 2024. Toward Responsible Recom- mender Systems. IEEE Intelligent Systems 39, 3 (2024), 5–12
work page 2024
-
[5]
Joseph Konstan and Loren Terveen. 2021. Human-centered Recommender Sys- tems: Origins, Advances, Challenges, and Opportunities.AI Magazine 42, 3 (2021), 31–42
work page 2021
-
[6]
Yuwen Liu, Xiaokang Zhou, Huaizhen Kou, Yawu Zhao, Xiaolong Xu, Xuyun Zhang, and Lianyong Qi. 2024. Privacy-preserving Point-of-interest Recom- mendation Based on Simplified Graph Convolutional Network for Geological Traveling. ACM Transactions on Intelligent Systems and Technology 15, 4 (2024), 1–17
work page 2024
-
[7]
Travis Lowdermilk. 2013. User-centered Design: a Developer’s Guide to Building User-friendly Applications. " O’Reilly Media, Inc. "
work page 2013
-
[8]
Ben Shneiderman. 2020. Human-centered Artificial Intelligence: Reliable, Safe & Trustworthy. International Journal of Human–Computer Interaction 36, 6 (2020), 495–504
work page 2020
Show all 19 references
-
[9]
Ítallo Silva, Leandro Marinho, Alan Said, and Martijn C Willemsen. 2024. Lever- aging ChatGPT for Automated Human-centered Explanations in Recommender Systems. In Proceedings of the 29th International Conference on Intelligent User Interfaces. 597–608
2024
-
[10]
Shoujin Wang, Xiuzhen Zhang, Yan Wang, and Francesco Ricci. 2024. Trustworthy Recommender Systems. ACM Transactions on Intelligent Systems and Technology 15, 4 (2024), 1–20
2024
-
[11]
Yunfan Wu, Qi Cao, Shuchang Tao, Kaike Zhang, Fei Sun, and Huawei Shen
-
[12]
Hyunsik Yoo, Zhichen Zeng, Jian Kang, Ruizhong Qiu, David Zhou, Zhining Liu, Fei Wang, Charlie Xu, Eunice Chan, and Hanghang Tong. 2024. Ensuring User-side Fairness in Dynamic Recommender Systems. In Proceedings of the ACM on Web Conference 2024. 3667–3678
2024
-
[13]
Kaike Zhang, Qi Cao, Fei Sun, Yunfan Wu, Shuchang Tao, Huawei Shen, and Xueqi Cheng. 2023. Robust Recommender System: a Survey and Future Directions. arXiv preprint arXiv:2309.02057 (2023)
2023 arXiv
-
[14]
Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, Huawei Shen, and Xueqi Cheng
-
[15]
Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, Huawei Shen, and Xueqi Cheng. 2024. LoRec: Combating Poisons with Large Language Model for Robust Sequential Recommendation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrie...
2024
-
[16]
In Proceedings of the 18th ACM Conference on Recommender Systems
Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System. In Proceedings of the 18th ACM Conference on Recommender Systems. 680–689
-
[17]
Bee and I need diversity!
Xiaofei Zhou, Yushan Zhou, Yunfan Gong, Zhenyao Cai, Annie Qiu, Qinqin Xiao, Alissa N Antle, and Zhen Bai. 2024. " Bee and I need diversity!" Break Filter Bubbles in Recommendation Systems through Embodied AI Learning. In Proceedings of the 23rd Annual ACM Interaction Design a...
2024
-
[18]
Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, Huawei Shen, and Xueqi Cheng. 2024. Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation. arXiv preprint arXiv:2410.22844 (2024)
2024 arXiv
-
[2024]
In Proceedings of the 18th ACM Conference on Recommender Systems
Accelerating the Surrogate Retraining for Poisoning Attacks against Rec- ommender Systems. In Proceedings of the 18th ACM Conference on Recommender Systems. 701–711
Reviewed August 12, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.