arsena-k/Word2Vec-bias-extraction

How are words loaded with meaning? Repository accompanying research by Alina Arseniev-Koehler and Jacob G. Foster, titled "Machine learning as a model for cultural learning: teaching an algorithm what it means to be fat." https://journals.sagepub.com/doi/full/10.1177/00491241221122603

34
/ 100
Emerging

This project helps social scientists and cultural researchers understand how language subtly embeds cultural biases, specifically focusing on body weight and health. By analyzing large text datasets, like news articles, it identifies what meanings (e.g., gender, morality, health, socio-economic status) are associated with words related to body weight. Researchers can input text data and receive quantified insights into underlying cultural schemata present in public discourse.

No commits in the last 6 months.

Use this if you are a social scientist or cultural researcher wanting to systematically uncover and measure hidden biases within text, particularly how concepts like gender or morality are implicitly linked to specific terms.

Not ideal if you need a quick, off-the-shelf tool for general text analysis or sentiment analysis without a deep interest in the nuanced, dimension-based extraction of cultural connotations.

sociology-research cultural-studies media-analysis bias-detection public-discourse
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

42

Forks

13

Language

Jupyter Notebook

License

Last pushed

Jul 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/arsena-k/Word2Vec-bias-extraction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.