- Researchers found 9% to 15% of Twitter accounts are bots and not humans
- With 319M accounts that means 48M of them are computer programs
- Experts identified 14M bot accounts using their own framework and analysis
- Sources said some bots are beneficial, as they alert people of natural disasters
Your last 'love', 'retweet' or 'follow' may not a man, a new study has found.
Researchers have discovered that up to 15 percent of Twitter accounts are bots, and with 319 million active users on the site, it is estimated that 48 million of them are computer programs.
While some robots can wreak havoc on Twitter, the sources revealedthat "numerous testimonies of bot are extremely beneficial", as they"warn people of natural disasters or points of view of customer service.
Researchers were able to identify nearly 14 million bot accounts on Twitter using their system and optimal threshold scores that separate human and bot accounts. During the analysis, the team also discovered the bots exhibited different types of behavior The recent survey on Twitter was conducted by the University of Southern California, whose 1 150 features among six classes to track accounts managed by the bots.
This includes data such as content of tweet and feelings, network and time series of activity models.
Researchers have discovered that up to 15 percent of Twitter accounts are bots and with 319 million active users on the site, it is estimate that 48 million of them are computer programs. Human users are represented in blue and bots are shown in red‘We benchmark the classification framework by using a publicly available dataset of Twitter bots,’ the researchers shared in the study published in
arXiv.
‘This training data is enriched by a manually annotated collection of active Twitter users that include both humans and bots of varying sophistication.’
BOT DETECTION FRAMEWORK
The team used over 1,150 features in six different classes to identify the bot accounts.
The classes are:
User-based features: Number of friends and followers, the number of tweets produced by the users, profile description and settings.
Friends features: Retweeting, mentioning, being retweeted, and being mentioned.
Network features: Retweet, mention, and hashtag co-occurrence networks.
Temporal features: Average rates of tweet production over various time periods and distributions of time intervals between events.
Content and language features: Looked at the nature of social media conversations.
For example, deceiving messages generally exhibit informal language and short sentences.
Sentiment features: Used several sentiment extraction techniques to generate various sentiment features, including arousal, valence and dominance scores, happiness score, polarization and strength and emoticon score.
Our high precision and agreement with the other performance models and can detect bots of different nature.
"Our estimates suggest that between 9% and 15% of the active Twitter accounts are bots."
However, sources said DailyMail.com that "while the robots usually have a negative connotation, many testimonies of bot are very beneficial, as those who automatically warn people of natural disasters (floods, earthquakes, tsunamis, air quality, etc.) or points of view of customer service.
The researchers also explained how these robots can work for large goods as well.
"Social bots perform useful functions, such as the dissemination of news and publications and the coordination of volunteer activities," they explained.
However, the team noted also that some computer programs have the ability to "emulate human behavior to make political support base of fake, to promote the recruitment and terrorist propaganda, to manipulate the stock market and spread rumors and conspiracy theories.
THE STAR WARS TWITTER BOTS
University College London found more than 350,000 Twitter bots working as a team.
And they have been named 'Star Wars bots' because they only posted random lines from the Star Wars novels.
A seperate study discovered a botnet that gathers the force of more than 350,000 bots. Dubbed Star Wars bots, these accounts were discovered in a small sample of the site and were found to only tweet random lines from Star Wars novels
Many of the citations began or ended with an incomplete word.
There are also hashtags inserted into random mail pieces.
Post 11 bots not more than tweets and max 10 followers and 31 friends. Experts believe that robots have also been created using a Windows smartphone.
However, all these accounts have been enough on 14 July 2013, which suggests the bots have been orchestrated and controlled by a botmaster.
When the team plotted the locations of these accounts on a map of the world, they discovered 3 244 of them were two rectangles in the North America, Europe and parts of North Africa.
The researchers were able to identify bot accounts almost 14 million on Twitter using their system and partitions of optimum threshold separating human and bot.
During the analysis, the team also discovered bots exposes the different types of behavior.
"Simple bots tends to retweet each other, while they frequently mention robots sophisticated," reads
the study.
"More sophisticated bots retweet, but do not mention humans."
"They may be unable to engage in exchanges with humans.
"While humans retweet also bots, as they can publish interesting content, they have no interest in mentioning the bots directly."
