Zzong's Notes

방문

Home

❯

논문

❯

Bias Fairness

❯

Clicks can be Cheating - Counterfactual Recommendation for Mitigating Clickbait Issue

Clicks can be Cheating - Counterfactual Recommendation for Mitigating Clickbait Issue

최초 작성 2026-08-28마지막 수정 2026-10-23읽는 데 1분

노트 편집 ↗
  • Related Work

    • Incorporating Various Feedback

      • negative experience identification
        • Between Clicks and Satisfaction - Study on Multi-Phase User Preferences and Satisfaction for Online News Reading
        • The good, the bad and the bait - Detecting and characterizing clickbait on YouTube
        • Effects of User Negative Experience in Mobile News Streaming
        • Leveraging Post-click Feedback for Content Recommendations

링크된 언급

1
clickbait

...d and the bait - Detecting and characterizing clickbait on YouTube Clicks can be Cheating - Counterfactual Recommendation for Mitigating Clickbait Issue

함께 보면 좋은 글

Between Clicks and Satisfaction - Study on Multi-Phase User Preferences and Satisfaction for Online News Reading

Abstract click signal does not capture post-click user experience: show that click signal does not align with user preference find that user preference changes frequently:

Leveraging Post-click Feedback for Content Recommendations

Post-click 을 click 으로 가정하고, click 을 vimp 로 가정하면 성립하지 않을까?

Effects of User Negative Experience in Mobile News Streaming

Introduction providing insights for the understanding of how negative experiences affect users’ behaviors and satisfaction, which is less studied in previous work

clickbait

일종의 클릭 낚시 현상 (issue) 으로, 시스템이 매력있는 썸네일 (attrative exposure features) 을 가지면서 실망스러운 콘텐츠 (dissatisfying content features) 를 가진 아이템을 자주 추천하는 현상을 의미한다.

Correcting for Selection Bias in Learning-to-rank Systems

selection bias, which occurs because clicked documents are reflective of what documents have been shown to the user in the first place. propose new counterfactual approaches...

Combating Selection Biases in Recommender Systems with a Few Unbiased Ratings

Tags selection bias, Abstract Introduction unbiased ratings 포함시키는 방법: 임의로 선택된 일부 아이템들에 대해 유저들에게 rating 을 요청함 Related work Recommendation Debiasing 기존의 debiasing 은 주로 두 가지 측면에...

Popularity Bias in Dynamic Recommendation

기존의 모든 popularity bias 연구들은 static 추천 task 를 기반으로 진행했지만, 실제 real-world 에서는 dynamic recommendation 형태를 띈다.

Causal Inference for Recommender Systems

“ 만약 사용자에게 강제로 영화를 보게 만든다면 어떻게 평가할 것인가?”: causal inference question

Denoising Implicit Feedback for Recommendation

implicit feedback 은 획득하기 쉬워서 data sparsity 를 완화하지만, 유저의 실제 만족도를 잘 반영하지 않는다: noisy

Calibrated Recommendations

Reference paper: https://dl.acm.org/doi/pdf/10.1145/3240323.3240372 cailbration 의 목적 In the recommended list of items, calibration ensures that the various (past) areas of...

  • Related Work
  • Incorporating Various Feedback