jiawei-chen

RecDebiasing: Find Research on Recommendation Bias

RecDebiasing is a curated collection of research papers, datasets, and code for recommendation debiasing. It organizes work by bias type, helping researchers and practitioners find relevant starting points across the field.

View on GitHub Compare
Stars
469
Forks
54
Stars, last 30 days
+0
Last commit
2.7 years ago
Contributors
4

Our take

Inactiveno commits in over a year

Health score

28/100

How it is scored
Activity
19
Community
53
Issues
21
Pull requests
20

+0 stars in the last 30 days

This is a broad research index rather than an implementation, and its inactive maintenance makes it best used as a discovery aid that readers verify against current sources.

Good fit if

  • You need a starting point for finding recommendation debiasing papers, datasets, and related code.
  • You want the literature organized by bias category rather than presented as a single undifferentiated bibliography.
  • You are prepared to check linked papers and repositories for current details.

Look elsewhere if

  • You need an installable library, runnable model, or maintained implementation; the repository is a collection of links.
  • You need a regularly updated bibliography, since there have been no commits in over a year and no releases in the past year.
  • You need project-level support or recent issue resolution; there has been no recent issue or pull-request activity.
All health signals
Last commit2024-02-19 (2.7 years ago)
Commits, last 90 days0
Releases, last 12 months0
Contributors4 (top contributor: 33% of commits)
Issues closed, last 90 days0
Pull requests merged, last 90 days0
Project age5 years

Checked on 2026-10-25 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

469

Forks

54

Change since Nov 16, 2026: 0 stars·0 forks

Overview

RecDebiasing is a research and resource index for recommendation debiasing. It collects papers, datasets, and links to code, with the goal of helping people explore how bias in recommender systems is studied and addressed.

Rather than implementing a debiasing method, the repository organizes existing work by topic, including selection, exposure, position, popularity, and fairness. It is useful as a literature-discovery resource, not as a software package or ready-to-run recommender system.

Key Features

  • Groups survey papers and datasets relevant to recommendation debiasing.
  • Organizes research by bias type, including selection, conformity, exposure, position, popularity, and unfairness.
  • Lists publication venues and links to papers for many entries.
  • Links to code repositories where implementations are available.
  • Includes work spanning multiple years and research areas, from causal methods to feedback loops.
  • Invites readers to suggest missing work or corrections.

Use Cases

  • Researchers starting a literature review can use the topic sections to identify relevant papers and follow their references.
  • Recommender-system practitioners comparing approaches can locate papers and linked implementations for a particular bias concern.
  • Students learning about recommendation bias can use the surveys and dataset links as an entry point.
  • Dataset users can find examples of commonly used datasets that include unbiased or randomized feedback.

Getting Started

Open the repository README and choose a topic or dataset section. Follow its paper, data, or code links for details. The repository does not describe an installation or execution command.

License in Plain Words

No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.

Considerations

The repository is marked inactive, with no commits in over a year and no releases in the past year. It has several contributors, and contribution activity is not concentrated in one person, but there has been no recent issue or pull-request activity. Treat the list as a useful snapshot rather than a guarantee of completeness or currency. The README provides links to external papers, datasets, and code, so availability and maintenance depend on those external destinations.

Found this useful?

Share it with someone who would like RecDebiasing.