arXiv cs.CY· Clair Kronk·· 13 小时前AI 评分31
Wikidata 人类条目覆盖偏差首次评估：女性仅占 28.71%
Initial Evaluation of Potential Bias in Coverage of Humans in Wikidata
AI 导读
一项开源审计平台通过 QLever 摄入 Wikidata 上超 600 万人类的逾 1000 万条陈述绑定，评估性别、性取向、地理、出生地城乡、族裔、多语言标签等维度的代表性偏差。
正文 · 原文
Abstract:Introduction. Open collaborative knowledge graphs such as Wikidata increasingly ground agentic artificial intelligence, information retrieval, and language modeling systems, making systematic auditing of their demographic representation and overall equity a research imperative. Methods. Herein, we present an open-source auditing platform that ingests over 10 million statement bindings representing over 6 million humans on Wikidata via QLever, and evaluates representation of gender, sexual orientation, geography, birthplace urbanicity, ethnicity, multilingual coverage of labels, descriptions, and aliases, occupation, and select intersectional pairs of these entities. It does so by making use of Chi-square goodness-of-fit tests, 95% Wilson-score confidence intervals, and disparity ratios, in light of Rubin's missingness taxonomy. Results. Women accounted for 28.71% (CI +/-0.04) of all humans in Wikidata with a stated gender. 38.26% of humans had a citizenship statement, with Western Europe and North America (WENA) representing approximately 53% of such statements. Among 1.8 million birthplaces that could be classified, rural birthplaces were observed in 2.48% of cases (in comparison to 27.4% global baseline). Fewer than 1.2% of entities carried an ethnicity statement, and non-English Wikidata descriptions covered 18.2% of items. Discussion. Our findings reveal significant missingness across the evaluated axes. Ethnicity and sexual orientation were the most critically under-documented (missing statements) while rural birthplaces and non-WENA citizenship were the most underrepresented.
| Comments: | 11 pages, 3498 words, 1 table, 5 figures. Fixed some typos (Figure X changed to Figure 2, Figure Y changed to Figure 3, Figure G changed to Figure 4, and Figure C changed to Figure 5) and made some text more clear (on page 4, it was not made clear that there were ~5 million citizenship statements total present on ~2.5 million instances of humans; the text has been modified to make that clear) |
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| ACM classes: | H.3.3; I.2.4; I.2.7; H.3.4; K.4.2 |
| Cite as: | arXiv:2609.22375 [cs.CY] |
| (or arXiv:2609.22375v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2609.22375 arXiv-issued DOI via DataCite |
Submission history
From: Clair Kronk [view email]
[v1]
Thu, 17 Sep 2026 19:48:54 UTC (598 KB)
[v2]
Thu, 22 Oct 2026 13:34:37 UTC (1,140 KB)
来源：arXiv cs.CY · arxiv.org