Celebrity Twitter accounts display 'bot-like' behavior

Celebrity Twitter accounts display 'bot-like' behavior

Celebrity Twitter accounts display 'bot-like' behavior

By Super User / Trending Posts / Monday, 30 November -0001 00:00
'Celebrity' Twitter accounts -- those with more than 10 million followers -- display more bot-like behavior than users with fewer followers, according to new research....

 elebrity' Twitter accounts - those with more than 10 million followers - show more bot-like behaviour than users with fewer followers, according to new research at the University of Cambridge.

The researchers used data from Twitter to determine whether bots can be accurately detected, how bots behave, and how they impact Twitter activity.

They divided accounts into categories based on a total number of followers and found that accounts with more than 10 million followers tend to retweet at similar rates to bots. 

The term 'bot' is often associated with spam, offensive content or political infiltration, but many reputable organisations in the world also rely on bots for their social media channels. 

"A Twitter user can be a human and still be a spammer, and an account can be operated by a bot and still be benign," said Zafar Gilani, a PhD student at Cambridge's Computer Laboratory, who led the research. 

"We're interested in seeing how effectively we can detect automated accounts and what effects they have," Gilani said. 

The findings are scheduled to be presented at the ongoing IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) in Sydney, Australia.

In order to determine whether an account was a bot (or not), the researchers looked at different characteristics of each account. 

These included the account creation date, average tweet frequency, content posted, account description, whether the user replies to tweets, likes or favourites received and the follower to friend ratio. 

A total of 3,535 accounts were analysed -- 1,525 were classified as bots and 2010 as humans.

The researchers found that bot accounts differ from humans in several key ways. Overall, bot accounts generate more tweets than human accounts. 


Bots have been on Twitter for the majority of the social network's existence - it has been estimated that anywhere between 40 and 60 per cent of all Twitter accounts are bots. 

Some bots have tens of millions of followers, although the vast majority have less than a thousand -- human accounts have a similar distribution.

The researchers said that despite the sheer volume of Tweets produced by bots, humans still have better quality and more engaging tweets - tweets by human accounts receive on average 19 times more likes and 10 times more retweets than tweets by bot accounts. 

Bots also spend less time liking other users' tweets, according to the study.

In another Study:

Nearly 48 million Twitter accounts are bots

A new study has estimated that as many as 48 million of Twitter’s users or up to 15 percent of active Twitter accounts on the microblogging website are so-called “bots” rather than people.

“Bots” are just software programs, designed to do everything a normal person on Twitter would do, including following other accounts and liking and retweeting certain messages.

In order to identify bot accounts on Twitter, researchers from University of Southern California (USC) and Indiana University in the U.S. used over 1,000 features in categories including friends, tweet content and sentiment and time between tweets.


“Our estimates suggest that between 9 percent and 15 percent of active Twitter accounts are bots,” they said.

Since, Twitter now has 319 million monthly active users that transforms to nearly 48 million bot accounts, using USC’s high-end estimate, reported CNBC.


A spokesperson from Twitter told CNBC that while bots may have negative connotations, “many bot accounts are extremely beneficial, like those that automatically alert people of natural disasters … or from customer service points of view.”

In February, Twitter estimated in a SEC filing that up to 8.5 percent of its users were not human, while the USC study’s authors say even its estimate of 15 percent is “conservative.”

“Many social bots perform useful functions, such as dissemination of news and publications,” however, “there is a growing record of malicious applications of social bots,” they said.

However, the USC report also points to the shortcoming of bots, saying that “there is a growing record of malicious applications of social bots. Some emulate human behavior to manufacture fake grassroots political support … [and]promote terrorist propaganda and recruitment.”


Twitter now has many other ways to account for violations, including impersonation accounts and spam. Also, several services occur which claim to be able to audit followers and categorize fake accounts.

Additionally, in the battle to fight online harassment, Twitter says users can silence notifications from accounts that have unconfirmed email address, phone number or profile picture that uses the default “egg” icon.

Login to post comments


Partly cloudy
E at 22.53 km/h /89%
16°C / 26°C
16°C / 25°C
14°C / 25°C

Please publish modules in offcanvas position.