New Machine Learning Framework Uncovers Twitter's Vast Bot Population - Motherboard

Up to 15 percent of active Twitter accounts are really bots: autonomous agents driven by algorithms rather than actual human personalities. The 15 percent figure comes courtesy of a new analysis by computer scientists at Indiana University and the University of Southern California using a machine learning framework designed to detect bots based on nearly a thousand distinct Twitter user characteristics. The group's work is described in a paper posted this week to the arXiv preprint server. On its face, this is a classic machine learning classification problem. Take some properties of an entity--screen name length, account age, and number of retweets per hour, for example--and look at those same properties across many different versions or instances of that entity along with some other property that we want to predict (whether an account is a bot or a human, in our case).