Subscribe now

Letter: To train a lie-detecting AI, just feed it some politics

Published 24 June 2020

From Sam Edge, Ringwood, Hampshire, UK

Dwight Hines suggests that court transcripts could be a source of training material for a linguistically based lie-detection algorithm Letters, 6 June.

I offer the pronouncements of our top politicians and their aides with respect to the pandemic and to climate change as a much richer seam of data to mine for this purpose.

Issue no. 3288 published 27 June 2020

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox. We'll also keep you up to date with New Scientist events and special offers.

Sign up
Piano Exit Overlay Banner Mobile Piano Exit Overlay Banner Desktop