The 6th FAccTRec Workshop on Responsible Recommendation at RecSys 2023 is a valuable catalyst for research and community-building around fairness, accountability, transparency, and related topics in recommender systems. In this workshop, we welcome research and position papers about ethical, social, and legal issues brought by the development and the use of recommendations that will support a discussion on providing and evaluating socially responsible recommendations.

We currently plan for this workshop to be a hybrid workshop, with an in-person component in Singapore in addition to a virtual component. Further details will be forthcoming, but physical attendance in Singapore will be encouraged if possible but not necessary to participate in the workshop.

This year, we are considering to collaborate with the NORMalize workshop, which discusses the normative design and evaluation of recommender systems.

Topics of Interest

FAccTRec stands for Fairness, Accountability, and Transparency in Recommender Systems and aims to draw attention to these issues at ACM RecSys, as has been done in the broader computer science community through events such as the FAccT conference. There are many potential aspects of responsibility in recommendation, including (but not limited to):

Responsibility: What does it mean for a recommender system to be socially responsible? How can we assess the social and human impact of recommender systems?

Fairness: What might ‘fairness’ mean in the context of recommendation? How could search and recommendation engines be unfair, and how could we measure such unfairness? How can we integrate user perceptions of fairness with its technical definitions?

Accountability: To whom, and under what standard, should a recommender system be accountable? How can or should it and its operators be held accountable? What harms should such accountability be designed to prevent?

Transparency: What is the value of transparency in search and recommendation, and how might it be achieved? How might it tradeoff with other important concerns? Can existing transparency methods be used for fair algorithms? How can it be defined and used for fairness-aware recommendation algorithms?

Safety: How can a recommender system be manipulated by adversarial parties? What is required to be resilient to such manipulation? How does private or sensitive information leak when searching or making recommendations? How to avoid such leakage? Can fair recommendations change users’ opinions?

Impact: In what ways has FAccT research on recommender systems, including fairness-aware recommendation methods, been impactful in industry or in research?

Authors working on these issues in Asia-Pacific contexts are encouraged to submit, (but papers from all areas of the world are welcome and will be reviewed without prejudice).

Submission Guidelines

We encourage submissions on the above topics. No official proceedings will be published because the focus of this workshop is a discussion about the directions to build and manage responsible recommender systems and provide feedback on early-stage research. All accepted papers’ manuscripts will be expected to be posted on arXiv.org by the authors. We allow manuscripts that have already been published or are currently submitted to another venue, so long as arXiv publication is compatible with that venue’s requirements; already-published manuscripts should be accompanied by a cover abstract justifying their contribution specifically to FAccTRec.

Manuscripts must be submitted through EasyChair and will be reviewed by our program committee. The review process is single-blind; the authors’ names do not need to be anonymized. Presentations will be held in an oral or a poster style.

Position Papers

Position papers address one or more of the above topics of interests or practical issues in building responsible recommendations. These could be either research systems or production systems in the industry.Position papers connecting FAccTRec topics to recent events or public discussions are also welcome.

Research Papers

Research papers present empirical or analytical results related to the social impact of recommendation algorithms, particularly around the topics above. These could be explorations of bias in recommender systems (either live systems or sandboxed algorithms), explainability, and transparency of recommendation responses, or experiments regarding the impact of the recommendation on its users or others, etc. We will interpret the topics broadly.

Paper format

All submissions should adopt the ACM manuscript / sigconf format with the subsequent options.

\setcopyright{none}

CCS class and keywords parts can be omitted.

In a case of position papers, the number of pages should be limited to three (3) pages in the ACM manuscript format and two (2) pages in the ACM sigconf format, and abstracts can be omitted from the article. In a case of research papers, the number of pages should be limited to ten (10) pages in the ACM manuscript format or six (6) pages in the ACM sigconf format. Note that an appendix is included, but references and acknowledgements are excluded from the page counts.

Submission

Papers should be submitted from EasyChair. Please do not forget to choose your type of submission: Position or Research.

Important Dates

  • 2023-08-03: Abstract registration deadline
  • 2023-08-07: Paper submission deadline
  • 2023-08-27: Author notification
  • 2023-09-10: Final version upload

TIMEZONE: Anywhere On Earth (UTC-12)