Iterated Algorithmic Bias in the Interactive Machine Learning Process of Information Filtering

Wenlong Sun, Olfa Nasraoui, Patrick Shafto

2018

Abstract

Early supervised machine learning (ML) algorithms have used reliable labels from experts to build predictions. But recently, these algorithms have been increasingly receiving data from the general population in the form of labels, annotations, etc. The result is that algorithms are subject to bias that is born from ingesting unchecked information, such as biased samples and biased labels. Furthermore, people and algorithms are increasingly engaged in interactive processes wherein neither the human nor the algorithms receive unbiased data. Algorithms can also make biased predictions, known as algorithmic bias. We investigate three forms of iterated algorithmic bias and how they affect the performance of machine learning algorithms. Using controlled experiments on synthetic data, we found that the three different iterated bias modes do affect the models learned by ML algorithms. We also found that Iterated filter bias, which is prominent in personalized user interfaces, can limit humans’ ability to discover relevant data.

Paper Citation

in Harvard Style

Sun W., Nasraoui O. and Shafto P. (2018). Iterated Algorithmic Bias in the Interactive Machine Learning Process of Information Filtering. In Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR; ISBN 978-989-758-330-8, SciTePress, pages 110-118. DOI: 10.5220/0006938301100118

in Bibtex Style

@conference{kdir18,
author={Wenlong Sun and Olfa Nasraoui and Patrick Shafto},
title={Iterated Algorithmic Bias in the Interactive Machine Learning Process of Information Filtering},
booktitle={Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR},
year={2018},
pages={110-118},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006938301100118},
isbn={978-989-758-330-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR
TI - Iterated Algorithmic Bias in the Interactive Machine Learning Process of Information Filtering
SN - 978-989-758-330-8
AU - Sun W.
AU - Nasraoui O.
AU - Shafto P.
PY - 2018
SP - 110
EP - 118
DO - 10.5220/0006938301100118
PB - SciTePress