ArticleLanguage and linguistics compass2021
Five sources of bias in natural language processing.
Article in Language and linguistics compass, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 38 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
38 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Using natural language processing in emergency medicine health service research: A systematic review and meta-analysis.Academic emergency medicine : official journal of the Society for Academic Emergency Medicine · 2024Pooled it
- Large Language Models for Mental Health Prediction: Scoping Review of Bias and Clinical Utility Documentation in 2019-2024.JMIR AI · 2026Review
- Cross-Cultural Validation of Manual and Automated Methods for Extracting Trauma Memory Features and Predicting PTSD in Young Populations.Research on child and adolescent psychopathology · 2026Article
- A fairness framework for natural language processing in substance use disorders and overdose.PLOS digital health · 2026Article
- Scoping review on natural language processing applications in counselling and psychotherapy.British journal of psychology (London, England : 1953) · 2026Article
- The role of AI in oncology: present applications and future horizons.NPJ precision oncology · 2026Review
- The potential and limitations of large language models for automatic classification of teachers' motivational messages in educational research.The British journal of educational psychology · 2026Review
- Article
- Article
- Fairness-aware artificial intelligence tutoring for multilingual learners: evaluating adaptive feedback across L1 and proficiency groups.Frontiers in artificial intelligence · 2026Article
- An LLM-based methodology for the automatic detection of bias in the DuoWikiBias corpus.Frontiers in artificial intelligence · 2026Article
- Corpus Linguistics as a Research Method in Nursing: A Practical Approach to Analysing Language Data.Journal of advanced nursing · 2025Article
- A Scoping Review of Methodological Approaches to Detect Bias in the Electronic Health Record.Stigma and health · 2025Article
- Benchmarking bias in embeddings of healthcare AI models: using SD-WEAT for detection and measurement across sensitive populations.BMC medical informatics and decision making · 2025Article
- Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback.Journal of medical Internet research · 2025Article
- Health Equity and Artificial Intelligence in Nephrology.Clinical journal of the American Society of Nephrology : CJASN · 2025Article
- Evaluating the Use of Generative Artificial Intelligence to Support Genetic Counseling for Rare Diseases.Diagnostics (Basel, Switzerland) · 2025Article
- Article
- Divided by discipline? A systematic literature review on the quantification of online sexism and misogyny using a semi-automated approach.Scientometrics · 2025Article
- Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods.JMIR medical informatics · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much of the recent work has focused on describing bias and providing an overview of bias in a larger context. Here, we provide a simple, actionable summary of this recent work. We outline five sources where bias can occur in NLP systems: (1) the data, (2) the annotation process, (3) the input representations, (4) the models, and finally (5) the research design (or how we conceptualize our research). We explore each of the bias sources in detail in this article, including examples and links to related work, as well as potential counter-measures.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.