Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue

Abstract

Recommendation is a prevalent and critical service in information systems. To provide personalized suggestions to users, industry players embrace machine learning, more specifically, building predictive models based on the click behavior data. This is known as the Click-Through Rate (CTR) prediction, which has become the gold standard for building personalized recommendation service. However, we argue that there is a significant gap between clicks and user satisfaction -- it is common that a user is "cheated" to click an item by the attractive title/cover of the item. This will severely hurt user's trust on the system if the user finds the actual content of the clicked item disappointing. What's even worse, optimizing CTR models on such flawed data will result in the Matthew Effect, making the seemingly attractive but actually low-quality items be more frequently recommended. In this paper, we formulate the recommendation models as a causal graph that reflects the cause-effect factors in recommendation, and address the clickbait issue by performing counterfactual inference on the causal graph. We imagine a counterfactual world where each item has only exposure features (i.e., the features that the user can see before making a click decision). By estimating the click likelihood of a user in the counterfactual world, we are able to reduce the direct effect of exposure features and eliminate the clickbait issue. Experiments on real-world datasets demonstrate that our method significantly improves the post-click satisfaction of CTR models.

Accepted by SIGIR 2021

References in corpus (2)

• Controlling Fairness and Bias in Dynamic Learning-to-Rank
• Market2Dish: Health-aware Food Recommendation

Cited by in corpus (22)

• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
• Deconfounded Recommendation for Alleviating Bias Amplification
• Generalizing to the Future: Mitigating Entity Bias in Fake News Detection
• Denoising Self-attentive Sequential Recommendation
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
• Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis
• User-controllable Recommendation Against Filter Bubbles
• Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
• CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation
• Debiasing Recommendation with Personal Popularity
• Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation
• Fairness of Exposure in Light of Incomplete Exposure Estimation
• Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
• Counterfactual Learning on Graphs: A Survey
• LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
• The Importance of Causality in Decision Making: A Perspective on Recommender Systems
• Adversarial Collaborative Filtering for Free
• Mitigating Spurious Correlations for Self-supervised Recommendation
• Brain Topography Adaptive Network for Satisfaction Modeling in Interactive Information Access System
• OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification
• Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
• ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling