Thomas Lumley • 9/27/2018

How to write a racist AI in R without really trying

Read Original

This article details an R-based replication of a Python experiment demonstrating how easily off-the-shelf tools can create a racially biased AI sentiment classifier. It covers using GloVe word embeddings, database techniques for handling large data, and glmnet for logistic regression modeling, highlighting inherent biases in standard NLP workflows.

0 comments
#NLP #Glove #Word Embeddings
How to write a racist AI in R without really trying

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
React, useEffect, and Stale Closures: How to Avoid Them with Dependencies and useRef
Jivbcoop • 4 votes
2
Better react-hook-form Smart Form Components
Maarten Hus • 2 votes
3
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
4
Quoting Thariq Shihipar
Simon Willison • 1 votes
5
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes
6
Using Browser Apis In React Practical Guide
Jivbcoop • 1 votes