Intentonomy-New Way to Study in Realtime FaceBook, Instagram Post Intentions
Sergie Belongie, Professor of
Computer Science at Cornell Tech, is thinking of how a new machine learning
system might find out the intentions behind an FB or Instagram post in real
time and help take action on them.
Content with malicious intent presents a major problem for Facebook, which is searching for a way to rapidly identify and remove harmful posts, such as the livestreaming of the March 15 mass shooting in New Zealand, amid a volume of content too vast for humans to moderate.
He calls it "intentonomy", the study of real intentions behind a social media post. It could be benign to polarizing to hateful. Bergie has received a $1.77 mn three year grant from Facebook for identifying malicious content in FB. There could be human nature, politics, tribal behaviour, monetary incentives behind postings.Belongie's team is also working on machine learning approaches for detecting forgeries.