Re:How I trained an AI to detect satire in under an hour
by minimaxir on Friday April 20, 2018 @04:25PM
(#16888204)
This has the same input data fidelity issues as the author's previous approach toward identifying fake news, which was flagged to death for being misleading: https://news.ycombinator.com/item?id=16128295
A sample size of 600 for text data is literally nothing for these types of models. (although atleast the classes are balanced this time)
A sample size of 600 for text data is literally nothing for these types of models. (although atleast the classes are balanced this time)