Inside Science August 31, 2018
Researchers at New York University developed a methodology for detecting bots on Twitter using an ensemble of classifiers and apply it to study bot activity within political discussions in the Russian Twittersphere focusing on the interval from February 2014 to December 2015. They found that on most days, the proportion of Tweets produced by bots exceeds 50%. They found that the software platform used for Tweeting is among the best predictors of bots. A recent report by RAND Corporation listed a number of recommendations for defending democracies in the advent of mal
icious bots and trolls on social media… read more. Open Access TECHNICAL ARTICLEÂ
Image credits: Abigail Malate, Staff Illustrator