BBC: "AI predicts outcome of human rights cases"
CNN: 'Our living dinosaurs' There are far fewer African elephants than we thought, study shows
The Smithsonian: "You Produce a Microbial Cloud That Can Act Like an Invisible Fingerprint"
Coverage in National Geographic by Ed Yong
A Reassuring Trunk: Evidence of Consolation in Elephants
How can data from one article be used for cluster size selection and parameter tuning for another article if the rows of the feature matrices (n-gram frequency matrices) across articles do not correspond with each other?