Mitigating Gender Bias in Machine Learning Data Sets
This addresses the issue of gender bias in AI systems, such as employment tools, which can perpetuate societal inequalities, but it is incremental as it builds on existing fairness and data analysis methods.
The paper tackles the problem of gender bias in machine learning by proposing a framework to identify bias in textual training data and neural word embeddings, drawing on gender theory and sociolinguistics to highlight pathways for bias removal and impact assessment.
Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given the complex way gender ideology is embedded in language. This paper proposes a framework for the identification of gender bias in training data for machine learning.The work draws upon gender theory and sociolinguistics to systematically indicate levels of bias in textual training data and associated neural word embedding models, thus highlighting pathways for both removing bias from training data and critically assessing its impact.