I’m auditing a University of Columbia course on data science at the moment. This lecture is on detecting truthfulness in human speakers. The researchers created a corpus of speech, some of which was truthful and some of which was not, and analysed various features to see how easy it would be to distinguish.
They also had human judges score the speech for truthfulness, and found:
– people performed, on average, worse than chance
– some people, however, performed much better than others
– training did not improve performance
– neuroticism in the scorer reduced performance
– agreeableness and openness in the scorer increased performance
– post-test confidence did not correlate with ability.
In a meta-study, criminals were found to have the best ability to distinguish between truth and lies, and parole officers the worst (less than 50%, possibly because they expect people to lie more than they actually do).
Leave a Reply