It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopedia

By Claudia Wagner, David García, Mohsen Jadidi, M. Strohmaier. 2015

283 citations recorded by the source corpus.

Wikipedia is a community-created encyclopedia that contains information about notable people from different countries, epochs and disciplines and aims to document the world's knowledge from a neutral point of view. However, the narrow diversity of the Wikipedia editor community has the potential to introduce systemic biases such as gender biases into the content of Wikipedia. In this paper we aim to tackle a sub problem of this larger challenge by presenting and applying a computational method for assessing gender bias on Wikipedia along multiple dimensions. We find that while women on Wikipedia are covered and featured well in many Wikipedia language editions, the way women are portrayed starkly differs from the way men are portrayed. We hope our work contributes to increasing awareness about gender biases online, and in particular to raising attention to the different levels in which gender biases can manifest themselves on the web.

Subfields: Communication, Sociology and Political Science, AI Ethics, Fairness & Society

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 Sociology and Political Science

In AI Ethics, Fairness & Society

Citations in the corpus

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation (2021, background): “Several works have shown that the distribution of demographics of Wikipedia authors is highly skewed resulting in various types of biases [9, 19, 36].”
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016, neutral): “[39] found that, as suggested by prior work on gender bias in language [2], articles about women more often emphasize their gender, their husbands and their husbands’ jobs, and other topics discussed consistently less often than in articles about men.”
Datasheet for the Pile (2022, background): “…dynamics has been widely studied, including 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,…”
Women through the glass ceiling: gender asymmetries in Wikipedia (2016, background): “In previous work we found that notable women and men from three different reference lists have equal probability of being represented in Wikipedia [36].”
Towards Understanding Gender Bias in Relation Extraction (2019, background): “This observation aligns with the literature, arguing that authors do not write about the two genders equally (Wagner et al., 2015; Graells-Garrido et al., 2015).”
Unsupervised Discovery of Implicit Gender Bias (2020, background): “Less-supervised approaches focus on corpuslevel analyses, such as associations between gendered terms and occupational stereotypes (Wagner et al., 2015; Bolukbasi et al., 2016; Fu et al., 2016; Joseph et al., 2017; Nakandala et al., 2017; Friedman et al., 2019; Chaloner and Maldonado, 2019; Hoyle…”
Reusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards (2021, methodology): “In one scenario, we consider a summarization model trained on a English Wikipedia, which is known to have various dimensions of gender bias (Wagner et al., 2015).”
Demographics of News Sharing in the U.S. Twittersphere (2017, background): “These studies can range from a simple characterization of to the investigation of more complex causes, including to raising attention to the different levels at which gender biases can manifest themselves on the web [41].”
Entity-Centric Contextual Affective Analysis (2019, methodology): “…people portray-als take either an unsupervised approach (Bam-man et al., 2013), which requires large amounts of data and can be difﬁcult to interpret, or rely on domain-speciﬁc knowledge (Fast et al., 2016; Wagner et al., 2015), which does not generalize well to other hypotheses and data domains.”
First Women, Second Sex: Gender Bias in Wikipedia (2015, result): “[50] focused on hyperlingual quantitative analysis, and obtained similar results for other languages.”
Word Embeddings and Gender Stereotypes in Swedish and English (2019, background): “As the popularity and usage of algorithms trained no natural language grows, there is a great risk that biases present in the training data, like how men and women are treated differently in Wikipedia articles [45, 46], will remain in the result and help propagate stereotypes.”
Twitter's Glass Ceiling: The Effect of Perceived Gender on Online Visibility (2016, background): “Studies show gender disparities on Wikipedia in content, contributors, and revisions for the top tier of Wikipedians (Wagner et al. 2015; Reagle and Rhue 2011; Lam et al. 2011; Antin et al. 2011; Lam et al. 2011).”
Towards a Standard for Identifying and Managing Bias in Artificial Intelligence (2022, background): “The training data, often scraped from internet sources, commonly has known gender, racial, cultural, and socio-economic biases [158, 159].”
Gender Bias in Machine Translation (2021, background): “In the lack of any available information, translators of five grammatical gender languages represented the character as either a man or a woman (Wandruszka, 1969; Nissen, 2002).”
Bias in Wikipedia (2017, background): “Wagner et al. [23] do their analysis regarding the dimensions coverage bias (number of articles about notable women compared to that of men), structural bias (links between Wikipedia articles, e.g. do articles about women link articles about men more often than vice versa?)”