PhD student Zafar Gilani recently presented the results of research on Twitter bots, at the International Conference on Advances in Social Networks Analysis and Mining in Sydney, Australia.
Twitter has more than 300 million monthly active users. But Gilani and his fellow researchers (Zafar Gilani, Ekaterina Kochmar, Jon Crowcroft: Classification of Twitter Accounts into Automated Agents and Human Users) have estimated that between about 30 million and 50 million of those are Twitter bots—automated accounts that do the bidding of their code-writing creators.
Zafar Gilani said “There could newsbots, and there could be spam bots. Or there could be bots doing political infiltration, which is obviously bad. Or social infiltration which could be bad.”
Gilani has built an algorithm to single out bots from human accounts, using factors like tweet frequency or content, and how much users interacted with other users. The system is able to tell bot from human 86 percent of the time.
Zafar is a member of the NetOS research group under the supervision of Professor Jon Crowcroft.