Twitter logo

Celebrity Tweeters behave like bots, study finds

Image credit: Dreamstime

While investigating the behaviour of bots on Twitter, University of Cambridge researchers found that Twitter users with more than 10 million followers tend to behave more like bots than other users.

Bots – which are estimated to make up between 40 and 60 per cent of all Twitter accounts – can be helpful, irritating or malicious, depending on their purpose. While many bots spam news feeds with offensive content and dodgy web links, others are used to organise and automate the sharing of helpful content.

For instance, the BBC and CNN rely on bots to share hundreds of news articles every day.

“A Twitter user can be a human and still a spammer, and an account can be operated by a bot and still be benign,” said Zafar Gilani, a PhD student who led the research at the University of Cambridge’s Computer Laboratory. “We’re interested in seeing how effectively we can detect automated accounts and what effects they have.”

In order to improve on current bot detection tools, the researchers took a manual approach to bot detection, inspecting thousands of accounts, and determining whether or not they were bots by looking at various factors including tweet frequency, type of content, and whether the user replies to tweets.

Consequently, they were able to build their own bot detection algorithm, which was 86 per cent accurate.

They found that bot accounts tweet more frequently, retweet more often, and redirect to external websites more than human users. The exception to this was the group of Twitter users with more than 10 million followers. These celebrity tweeters tend to have strong similarities with bots, with a faster pace of tweeting and a higher rate of retweets.

“We think this is probably because bots aren’t that good at creating original Twitter content, so they rely a lot more on retweets and redirecting followers to external websites,” said Mr Gilani. “While bots are getting more sophisticated all the time, they’re still pretty bad at one-on-one Twitter conversations, for instance, most of the time a conversation with a bot will be mostly gibberish.”

“Many people tend to think that bots are nefarious or evil, but that’s not true,” he continued. “They can be anything, just like a person. Some of them aren’t exactly legal or moral, but many of them are completely harmless […] what is clear though is that bots are here to stay.”

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles