This post explores how bias can creep into word embeddings like word2vec, and I thought it might make it more fun (for me, at least) if I analyze a model trained on what you, my readers (all three of you), might have written.
Often when we talk about bias in word embeddings, we are talking about such things as bias against race or sex. But I’m going to talk about bias a little bit more generally to explore attitudes we have that are manifest in the words we use about any number of topics.
Blog Editors
Recent Updates
- DOJ’s West Coast Strike Force to Target Health Care Fraud in Arizona, Nevada, and Northern California
- DOJ FOCUS Initiative Prioritizes “High Quality” Data Miner Actions by FCA Whistleblowers
- FDA Proposal Would Leave Semaglutide, Tirzepatide, and Liraglutide Off 503B Bulks List
- The DOJ’s Bulk Sensitive Data Rule and Your Obligation to “Know Your Reporting Requirements”
- Is Your Product Ready to Be Listed? What the Dietary Supplement Listing Act of 2026 Means for Your Business