Fake news is the buzz word of the year, or at least it feels that way. Everyone claims to know it when they see it, many produce it (intentionally or otherwise), but is there anything that can really be done about it? This interesting information came to us from Motherboard in their article, “Teaching Machines to Detect Fake News Is Really Hard.”
Researchers combined metadata with over 10,000 examples of “real” fake news in a data set to train machine learning algorithms how to automatically detect fake news. This can be challenging because one of the most difficult parts of limiting the spread of fake news is that humans have a hard time filtering what is legit from what is bogus. So if humans can’t tell the difference between what’s real and fake, could machines do any better?
In an attempt to answer this question, computer scientist William Wang created LIAR, the largest ever database of fake news in an effort to train machines to automatically detect deception. After much work to tag items correctly and train the machine to use deep learning on text data, the system achieved a 27% accuracy rate, which is 35% better than the computer randomly guessing.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.