Never miss a great news story!
Get instant notifications from Economic Times
AllowNot now


You can switch off notifications anytime using browser settings.
11,856.80-80.7
Stock Analysis, IPO, Mutual Funds, Bonds & More

Turning to the machines: New algorithm uses ML to identify cyber-bullies on Twitter

The algorithms 'learn' how to tell the difference between bullies and typical users by weighing certain features.

IANS|
Sep 17, 2019, 06.07 PM IST
0Comments
It seems counter intuitive – after all, social media helps you share your opinions and speak to a larger audience. But thanks to rampant identity theft and online stalking, there is a solid argument to be made to target your social posts instead of keeping them public. Karan Bajaj shows you how.
It seems counter intuitive – after all, social media helps you share your opinions and speak to a larger audience. But thanks to rampant identity theft and online stalking, there is a solid argument to be made to target your social posts instead of keeping them public. Karan Bajaj shows you how.
NEW YORK: Researchers have developed machine learning algorithms which can identify bullies and aggressors on Twitter with 90 per cent accuracy.

For the study published in the journal Transactions on the Web, the research team analysed the behavioural patterns exhibited by abusive Twitter users and their differences from other users.

"We built crawlers - programs that collect data from Twitter via variety of mechanisms," said study researcher Jeremy Blackburn from Binghamton University in the US.

"We gathered tweets of Twitter users, their profiles, as well as (social) network-related things, like who they follow and who follows them," Blackburn said.

The researchers then performed natural language processing and sentiment analysis on the tweets themselves, as well as a variety of social network analyses on the connections between users.

Facebook, Twitter Instagram: Tips & Tricks To Keep Social Media Private

of 9
Next
Prev
Play Slideshow

Protect Data

21 Feb, 2019
It seems counter intuitive – after all, social media helps you share your opinions and speak to a larger audience. But thanks to rampant identity theft and online stalking, there is a solid argument to be made to target your social posts instead of keeping them public. Karan Bajaj shows you how.
Next

They developed algorithms to automatically classify two specific types of offensive online behaviour, i.e. cyber-bullying and cyber-aggression.

The algorithms were able to identify abusive users - who engage in harassing behaviour like those who send death threats or make racist remarks - on Twitter with 90 per cent accuracy.

"In a nutshell, the algorithms 'learn' how to tell the difference between bullies and typical users by weighing certain features as they are shown more examples," said Blackburn.

"Our research indicates that machine learning can be used to automatically detect users that are cyber-bullies, and thus could help Twitter and other social media platforms remove problematic users," Blackburn added.
Want stories like this in your inbox? Sign up for the daily ET Panache newsletter.

You can also follow us on Facebook, Twitter and LinkedIn.

Also Read

Twitter boards Paytm’s app

Mastodon cashing in on Twitter’s failings

#Cancelallblueticksin India row erupts on Twitter

Trump turns Rocky on Twitter, image goes viral

'Game of Thrones' in Maharashtra: Twitter erupts with memes

Comments
Add Your Comments
Commenting feature is disabled in your country/region.
Download The Economic Times Business News App for the Latest News in Business, Sensex, Stock Market Updates & More.

Popular Categories


Other useful Links


Follow us on


Download et app


Copyright © 2019 Bennett, Coleman & Co. Ltd. All rights reserved. For reprint rights: Times Syndication Service