First Women, Second Sex: Gender Bias in Wikipedia

By Eduardo Graells-Garrido, Mounia Lalmas, Filippo Menczer. 2015

117 citations recorded by the source corpus.

Contributing to the writing of history has never been as easy as it is today. Anyone with access to the Web is able to play a part on Wikipedia, an open and free encyclopedia, and arguably one of the primary sources of knowledge on the Web. In this paper, we study gender bias in Wikipedia in terms of how women and men are characterized in their biographies. To do so, we analyze biographical content in three aspects: meta-data, language, and network structure. Our results show that, indeed, there are differences in characterization and structure. Some of these differences are reflected from the off-line world documented by Wikipedia, but other differences can be attributed to gender bias in Wikipedia content. We contextualize these differences in social theory and discuss their implications for Wikipedia policy.

Subfields: Communication, Gender Studies, Sociology and Political Science, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Gender Studies

In Sociology and Political Science

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus (2021, background): “Second, even for topics it does cover, there might be biases that cannot be resolved without looking at a broader context (Wagner et al., 2016; Graells-Garrido et al., 2015).”
It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution (2019, background): “…predicates that all content should be presented without bias, women are nonetheless less likely to be deemed “notable” than men of equal stature (Reagle and Rhue, 2011), and there are differences in the choice of language used to describe them (Bamman and Smith, 2014; Graells-Garrido et al., 2015).”
A Distributional Approach to Controlled Text Generation (2020, background): “One of those demographics is women, whose biographies make up only 18.58% of English Wikipedia’s biographies (Graells-Garrido et al., 2015).”
Datasheet for the Pile (2022, background): “…along the lines of race [Adams et al., 2019, Xing and Vetter, 2020], gender [Reagle and Rhue, 2011, Wagner et al., 2015, Hargittai and Shaw, 2015, Graells-Garrido et al., 2015], ability [Phillips, 2016, Derby, 2012], nation of origin [Rask, 2008, Lee and Chun, 2017], religion [Callahan and…”
Women through the glass ceiling: gender asymmetries in Wikipedia (2016, methodology): “Internal Wikipedia discussions that started after we published our preliminary studies on gender inequalities in the content of Wikipedia [16, 36] suggest such actions7.”
Towards Understanding Gender Bias in Relation Extraction (2019, methodology): “…since words pertaining to marriage are more often mentioned in Wikipedia articles about female entities and words pertaining to hypernym (which is similar to occupation) are more often mentioned in Wikipedia articles about male entities (Wagner et al., 2015; Graells-Garrido et al., 2015).”
SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets (2021, background): “Moreover, real data contains biases such as the fact that mathematicians are more often men or that most biographies on English Wikipedia are of Americans and Europeans [54, 25, 18].”
A Taxonomy of Knowledge Gaps for Wikimedia Projects (First Draft) (2020, background): “The gender gap – the fact that the majority of Wikimedia content about people focuses on male subjects – is one of the most-studied examples of content gaps and well-documented in the research literature [3, 14, 31, 69, 75, 81, 92, 102, 136, 142, 167, 168, 210, 211] and interactive tools such as the”
Bias in Wikipedia (2017, background): “Several studies have analyzed the representation of women in Wikipedia compared to that of men ([23, 19, 11]).”
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection (2022, background): “This imbalance is reflected in who gets written about, and how (Bamman and Smith, 2014; Graells-Garrido et al., 2015; Wagner et al., 2015).”