This book constitutes the refereed proceedings of the 4th International Workshop on Algorithmic Bias in Search and Recommendation, BIAS 2023, held in Dublin, Ireland, in April 2023.
The 10 full papers and 4 short papers included in this book were carefully reviewed and selected from 36 submissions. The present recent research in the following topics: biases exploration and assessment; mitigation strategies against biases; biases in newly emerging domains of application, including healthcare, Wikipedia, and news, novel perspectives; and conceptualizations of biases in the context of generative models and graph neural networks.
A Study on Accuracy, Miscalibration, and Popularity Bias in
Recommendations.- Measuring Bias in Multimodal Models: Multimodal Composite
Association Score.- Evaluating Fairness Metrics.- Utilizing Implicit Feedback
for User Mainstreaminess Evaluation and Bias Detection in Recommender
Systems.- Preserving Utility in Fair Top-k Ranking with Intersectional
Bias.- Mitigating Position Bias in Hotels Recommender Systems.- Improving
Recommender System Diversity with Variational Autoencoders.- Addressing
Biases in the Texts using an End-to-End Pipeline Approach.- Bootless
Application of Greedy Re-ranking Algorithms in Fair Neural Team
Formation.- How do you feel? Information Retrieval in Psychotherapy and Fair
Ranking Assessment.- Understanding Search Behavior Bias in Wikipedia.- Do you
MIND? Reflections on the MIND dataset for research on diversity in news
recommendations.- Detecting and Measuring Social Bias of Arabic Generative
Models in the Context of Search and Recommendation.- What are we missing in
algorithmic fairness? Discussing open challenges for fairness analysis in
user profiling with Graph Neural Networks.
