How do you know if you're reading tweets from a real person or a bot? As bot technology becomes more sophisticated it's increasingly hard to tell. Researchers at Duo Security have collected and analyzed data from 88 million public Twitter accounts using machine learning to spot the tactics used by malicious bots to appear legitimate and avoid detection. The analysis included the application of 20 unique account characteristics in a machine learning model to differentiate a human Twitter account, classified as 'genuine' in the study, from a bot. These characteristics include, among other things, the time between tweets, distinct tweet…
[Continue Reading]