Hong Kong Protests: Using Natural Language Processing for Fake News Detection on Twitter

Artificial Intelligence Applications and Innovations · 2020 · PMC7256559

Europe PMC

hedged sentence

—

closest p

—

boldest claim

The sentences

could be considered significantno p-value reported

Since the impact of a tweet spreading fake news could be considered significant, one could argue that models achieving higher recall scores would be preferred, even if precision scores suffered somewhat.

also in 229 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.