Is Wikipedia succeeding in reducing gender bias? Assessing changes in gender bias in Wikipedia using word embeddings

Abstract

Large text corpora used for creating word embeddings (vectors which represent word meanings) often contain stereotypical gender biases. As a result, such unwanted biases will typically also be present in word embeddings derived from such corpora and downstream applications in the field of natural language processing (NLP). To minimize the effect of gender bias in these settings, more insight is needed when it comes to where and how biases manifest themselves in the text corpora employed. This paper contributes by showing how gender bias in word embeddings from Wikipedia has developed over time. Quantifying the gender bias over time shows that art related words have become more female biased. Family and science words have stereotypical biases towards respectively female and male words. These biases seem to have decreased since 2006, but these changes are not more extreme than those seen in random sets of words. Career related words are more strongly associated with male than with female, this difference has only become smaller in recently written articles. These developments provide additional understanding of what can be done to make Wikipedia more gender neutral and how important time of writing can be when considering biases in word embeddings trained from Wikipedia or from other text corpora.

Assessing Gender Bias in Wikipedia: Inequalities in Article Titles

“…13 The editors' community is consequently tackling this problem and fighting the gender gap. As recently shown by Schmahl et al (2020), these efforts pay off and not only more biographies about women are being added, but also NLP models such as word embeddings trained on Wikipedia articles are exhibiting less stereotypical biases.…”

“…In their following analysis, Wagner et al (2016) showed that gender inequalities can be observed also on other dimensions, e.g., women have to be more notable to have their biographies than men. These patterns occurring in Wikipedia have been shown to directly influence NLP models, such as word embeddings (Schmahl et al, 2020) or relation extraction (Gaut et al, 2020).…”