US Department of Homeland Security
is funding research into teaching computers to distinguish opinions
from fact in written text.
Cornell University professor
Claire Cardie and associates from
other universities will use machine learning algorithms to scan text
examples containing fact and opinion with the goal to distinguish the
"Lots of work has been done on
extracting factual information — the who, what, where, when,"
explained Cardie. "We're interested in seeing how we would
extract information about opinions."
the obvious ramifications to
the veracity of Slashdot discussions is this a good thing for US