Boratto / Faralli / Marras Advances in Bias and Fairness in Information Retrieval

4th International Workshop, BIAS 2023, Dublin, Ireland, April 2, 2023, Revised Selected Papers
1. Auflage 2023
ISBN: 978-3-031-37249-0
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 1840, 177 Seiten, eBook

Reihe: Communications in Computer and Information Science

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.

Zielgruppe

Research

Autoren/Hrsg.

Boratto, Ludovico

Faralli, Stefano

Marras, Mirko

Stilo, Giovanni

Inhaltsverzeichnis

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.