Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Concerns about gender bias in word embedding models have captured substantial attention in the algorithmic bias research literature. Other bias types however have received lesser amounts of scrutiny. This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, physical appearance, sexual orientation, religious sentiment and political leanings. Consistent with previous scholarly literature, this work has found systemic bias against given names popular among African-Americans in most embedding models examined. Gender bias in embedding models however appears to be multifaceted and often reversed in polarity to what has been regularly reported. Interestingly, using the common operationalization of the term bias in the fairness literature, novel types of so far unreported bias types in word embedding models have also been identified. Specifically, the popular embedding models analyzed here display negative biases against middle and working-class socioeconomic status, male children, senior citizens, plain physical appearance and intellectual phenomena such as Islamic religious faith, non-religiosity and conservative political orientation. Reasons for the paradoxical underreporting of these bias types in the relevant literature are probably manifold but widely held blind spots when searching for algorithmic bias and a lack of widespread technical jargon to unambiguously describe a variety of algorithmic associations could conceivably be playing a role. The causal origins for the multiplicity of loaded associations attached to distinct demographic groups within embedding models are often unclear but the heterogeneity of said associations and their potential multifactorial roots raises doubts about the validity of grouping them all under the umbrella term bias. Richer and more fine-grained terminology as well as a more comprehensive exploration of the bias landscape could help the fairness epistemic community to characterize and neutralize algorithmic discrimination more efficiently.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 9×
“This method allows FastText to compute word representations for out of vocabulary words (words that did not appear in the training corpus).”
MethodInfluentialLiberals and conservatives rely on different sets of moral foundations.
Graham, J., Haidt, J., & Nosek, B. A. (2009) · Journal of Personality and Social Psychology · doi:10.1037/a0015141 · Cited by 4,560
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 5×
“Popular machine learning artifacts have been used to illustrate the creeping of purported societal biases and prejudices into models used for computer vision [1], recidivism prediction [2] or language modeling [3].”
BackgroundInfluentialField, A. P., & Gillett, R. (2010) · British Journal of Mathematical and Statistical Psychology · doi:10.1348/000711010x502733 · Cited by 1,162
Algorithmic Decision Making and the Cost of Fairness
Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., & Huq, A. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098095 · Cited by 1,149
Word embeddings quantify 100 years of gender and ethnic stereotypes
Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1720347115 · Cited by 1,065 · cited 2×
“Word embedding models have been claimed to capture prejudicial bias, stemming from the corpus on which they were trained, against women and ethnic minorities [7].”
BackgroundBias detectives: the researchers striving to make algorithms fair
Courtland, R. (2018) · Nature · doi:10.1038/d41586-018-05469-3 · Cited by 205 · cited 1×
“Popular machine learning artifacts have been used to illustrate the creeping of purported societal biases and prejudices into models used for computer vision [1], recidivism prediction [2] or language modeling [3].”
Background
Cited by
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050
“lyzing “bias” in NLP systems often state multiple motivations (e.g., Hovy and Spruit, 2016; Bender, 2019; Sun et al., 2019; Rozado, 2020; Shah et al., 2020).”
BackgroundInfluentialCrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Nangia, N., Vania, C., Bhalerao, R., & Bowman, S. R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.154 · Cited by 446
Algorithmic bias in data-driven innovation in the age of AI
Akter, S., McCarthy, G., Sajib, S., Michael, K., Dwivedi, Y. K., D’Ambra, J., & Shen, K. N. (2021) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2021.102387 · Cited by 440
The Political Biases of ChatGPT
Rozado, D. (2023) · Social Sciences · doi:10.3390/socsci12030148 · Cited by 281
“The topic of political bias in AI systems has received a comparatively limited amount of attention in comparison to other algorithmic bias types (Rozado 2020).”
BackgroundSelf-citationA framework for AI-powered service innovation capability: Review and agenda for future research
Akter, S., Hossain, M. A., Sajib, S., Sultana, S., Rahman, M., Vrontis, D., & McCarthy, G. (2023) · Technovation · doi:10.1016/j.technovation.2023.102768 · Cited by 274
Metadata
- Authors
- Rozado, D.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2020-04-21
- Volume
- 15
- Issue
- 4
- Pages
- e0231189
- ISSN
- 1932-6203 (ISSN-L)
- OpenAlex
- W3016719704
- Cited by
- 51
- References
- 8
- FWCI
- 8.17
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types. https://app.cochat.ai/papers/10.1371/journal.pone.0231189
- The paper
- Rozado, D. (2020). Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types. PLOS ONE. https://doi.org/10.1371/journal.pone.0231189
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.