Indiana University researchers have developed a new app that identifies Twitter accounts controlled by automated software designed to flood online conversations with spam and misleading information, the researchers say.
The BotOrNot app examines about 1,000 account features including the userâ€™s network, content and posting frequency to determine the extent to which an account resembles a social bot.
â€œWe have applied a statistical learning framework to analyze Twitter data, but the â€˜secret sauceâ€™ is in the set of more than one thousand predictive features able to discriminate between human users and social bots, based on content and timing of their tweets, and the structure of their networks,â€ said Alessandro Flammini, associate professor of informatics and principal investigator on the project.
This projectâ€™s goal is to discover how many accounts are bot-controlled.
â€œAre there thousands of social bots? Millions? We know there are lots of bots out there, and many are totally benign. But we also found examples of nasty bots used to mislead, exploit and manipulate discourse with rumors, spam, malware, misinformation, political astroturf and slander,â€ says Fil Menczer, another researcher.
The researchers posted a few examples on the applicationâ€™s main page. Based on their score, two Justin Bieber fan accounts, @jusbieberphotos and @stanbieberfan, show an 80 per cent probability of being software-controlled.
The developersâ€™ ultimate goal is to eradicate untruthful information that might favor cybercrime, cause confusion and even endanger peopleâ€™ democratic rights.