Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English

Su Lin Blodgett

100 citations0/0 files storedarXiv (Cornell University)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Natural Language Processing Techniques Authorship Attribution and Profiling

Abstract

We highlight an important frontier in algorithmic fairness: disparity in the quality of natural language processing algorithms when applied to language from authors of different social groups. For example, current systems sometimes analyze the language of females and minorities more poorly than they do of whites and males. We conduct an empirical analysis of racial disparity in language identification for tweets written in African-American English, and discuss implications of disparity in NLP.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 100 citations exist upstream.

References

1975Language in the inner city: studies in the Black English Vernacular. By William Labov. Philadelphia: University of Pennsylvania Press, 1972. Pp. xxiv, 412. $6.95.2015Certifying and Removing Disparate Impact 2004African American English: A Linguistic Introduction 1999African American Vernacular English: Features, Evolution, Educational Implications 2016The Social Impact of Natural Language Processing 2015Challenges of studying and processing dialects in social media

Cited by

2021More than a biomarker: could language be a biosocial marker of psychosis?2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics 2019A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings 2019Validity Concerns in Research Using Organic Data 2021Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement 2022Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models 2023Fairness in Language Models Beyond English: Gaps and Challenges

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.