Scientists from Binghamton University have developed a new machine-learning algorithm that claims to spot cyberbullies on Twitter with 90 per cent accuracy. Researchers believe tools for detecting harmful actions on social media are scarce, quite rightly so. Given its ambiguous nature, cyber-bullying is often difficult to detect. study was published in journal Transactions on Web.

Analysis

As part of study, scientists analysed behavioural patterns in abusive Twitter users. Scientists also analysed how those behavioural patterns differ from or Twitter users.

"We built crawlers -- programmes that collect data from Twitter via variety of mechanisms," said Binghamton University computer scientist Jeremy Blackburn. "We gared tweets of Twitter users, ir profiles, as well as (social) network-related things, like who y follow and who follows m," Blackburn said.

Indians fear losing job due to controversial social media posts: Study

Methodology

Researchers performed natural langu processing and sentiment analysis on tweets posted by abusive users. Scientists also analysed connections between different abusive users. Algorithms furr classified Twitterati's abusive behaviour into one of se s: Cyberbullying or cyberaggression. Researchers reached a conclusion that se are users who eng in harassing behaviour and send death threats or make racist remarks towards or users.

"In a nutshell, algorithms 'learn' how to tell difference between bullies and typical users by weighing certain features as y are shown more examples," said Blackburn "One of biggest issues with cyber safety problems is dam being done is to humans, and is very difficult to 'undo."

Twitter disables SMS tweets after CEO account gets hacked

Conclusion

Research indicates that machine learning can be used to automatically detect cyberbullies. This could help Twitter and or social media platforms detect and take appropriate action on abusive users. Scientists ackwledge such a system can only identify cyberbullies and t actually prevent m.

"And unfortunate truth is that even if bullying accounts are deleted, even if all ir previous attacks are deleted, victims still saw and were potentially affected by m," Blackburn said.

(With PTI inputs)