Enhancing Explainable Matrix Factorization with Tags for Multi-Style Explanations

Olurotimi Seton, Pegah Haghighi, Mohammed Alshammari, Olfa Nasraoui

2023

Abstract

Black-box AI models tend to be more accurate but less transparent and scrutable than white-box models. This poses a limitation for recommender systems that rely on black-box models, such as Matrix Factorization (MF). Explainable Matrix Factorization (EMF) models are “explainable” extensions of Matrix Factorization, a state of the art technique widely used due to its flexibility in learning from sparse data and accuracy. EMF can incorporate explanations derived, by design, from user or item neighborhood graphs, among others, into the model training process, thereby making their recommendations explainable. So far, an EMF model can learn a model that produces only one explanation style, and this in turn limits the number of recommendations with computable explanation scores. In this paper, we propose a framework for EMFs with multiple styles of explanation, based on ratings and tags, by incorporating EMF algorithms that use scores derived from tagcentric graphs to connect rating neighborhood-based EMF techniques to tag-based explanations. We used precalculated explainability scores that have been previously validated in user studies that evaluated user satisfaction with each style individually. Our evaluation experiments show that our proposed methods provide accurate recommendations while providing multiple explanation styles, without sacrificing the accuracy of the recommendations.

Paper Citation

in Harvard Style

Seton O., Haghighi P., Alshammari M. and Nasraoui O. (2023). Enhancing Explainable Matrix Factorization with Tags for Multi-Style Explanations. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-671-2, SciTePress, pages 75-85. DOI: 10.5220/0012189900003598

in Bibtex Style

@conference{kdir23,
author={Olurotimi Seton and Pegah Haghighi and Mohammed Alshammari and Olfa Nasraoui},
title={Enhancing Explainable Matrix Factorization with Tags for Multi-Style Explanations},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2023},
pages={75-85},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012189900003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Enhancing Explainable Matrix Factorization with Tags for Multi-Style Explanations
SN - 978-989-758-671-2
AU - Seton O.
AU - Haghighi P.
AU - Alshammari M.
AU - Nasraoui O.
PY - 2023
SP - 75
EP - 85
DO - 10.5220/0012189900003598
PB - SciTePress