A team of researchers, including faculty at Binghamton University, have developed machine learning algorithms which can successfully identify bullies and aggressors on Twitter with 90 percent accuracy.
Effective tools for detecting harmful actions on social media are scarce, as this type of behavior is often ambiguous in nature and/or exhibited via seemingly superficial comments and criticisms. Aiming to address this gap, a research team featuring Binghamton University computer scientist Jeremy Blackburn analyzed the behavioral patterns exhibited by abusive Twitter users and their differences from other Twitter users.
“We built crawlers — programs that collect data from Twitter via variety of mechanisms,” said Blackburn. “We gathered tweets of Twitter users, their profiles, as well as (social) network-related things, like who they follow and who follows them.”
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. The researchers developed algorithms to automatically classify two specific types of offensive online behavior, i.e., cyberbullying and cyberaggression. The algorithms were able to identify abusive users on Twitter with 90 percent accuracy. These are users who engage in harassing behavior, e.g. those who send death threats or make racist remarks to users.
“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.
While this research can help mitigate cyberbullying, it is only a first step, said Blackburn.
“One of the biggest issues with cyber safety problems is the damage being done is to humans, and is very difficult to ‘undo,'” Said Blackburn. “For example, our research indicates that machine learning can be used to automatically detect users that are cyberbullies, and thus could help Twitter and other social media platforms remove problematic users. However, such a system is ultimately reactive: it does not inherently prevent bullying actions, it just identifies them taking place at scale. And the unfortunate truth is that even if bullying accounts are deleted, even if all their previous attacks are deleted, the victims still saw and were potentially affected by them.”
Blackburn and his team are currently exploring pro-active mitigation techniques to deal with harassment campaigns.
The Latest on: Cyberbullying and cyberaggression
via Google News
The Latest on: Cyberbullying and cyberaggression
- An atmosphere of intrafamily trust tends to prevent problematic internet useon April 8, 2021 at 9:12 am
Cyberbullying already accounts for one in four cases of bullying and, according to the latest UNICEF report issued on the occasion of Safer Internet Day, it affects at least two students per class ...
- Psychology Todayon April 8, 2021 at 1:16 am
2017; Pitchforth et al., 2018). Other factors might include the growing negative influence of social media and cyberbullying on young adults, economic downturns in the early and mid-2000s ...
- Psychology Todayon April 6, 2021 at 4:18 am
2017; Pitchforth et al., 2018), and such factors might include the growing negative influence of social media and cyberbullying on young adults (Jacobsen & Forste, 2011; Davey ...
- International journal of environmental research and public healthon March 19, 2021 at 5:00 pm
I-DECIDE: A Social Prescribing and Digital Intervention Protocol to Promote Sexual and Reproductive Health and Quality of Life among Young Cape Verdeans.
- Raab: Russia's aggression and propaganda remains a threaton March 16, 2021 at 5:13 am
Foreign Secretary Dominic Raab says Russia remains a threat to the UK due to its "cyber aggression, propaganda, and misinformation" - citing the poisoning of Alexei Navalny as proof it is still using ...
- Violence and victimson February 22, 2021 at 4:00 pm
Co-occurrence of Dating Violence Victimization Subtypes: Assessing the Influence of Family Factors, Dating Attitudes, Risky Behaviors, and the Moderating Effect of Gender Among School-Aged Teens.
- The Russian Federationon August 9, 2020 at 12:04 am
More than half face cyberaggression. Exposure to inappropriate or harmful content online – content risks – are in second place (76% of those aged 14 to 17 and 54% of those aged 12 to 13). One out of ...
- Czech Republicon July 29, 2020 at 5:12 am
Regarding cyberaggression, girls, as well as younger children, were more upset after being attacked online. The highest percentage of cyber aggressors was among older boys aged 13 to 17 (19%), more ...
- PhD students and postgraduate research study optionson May 13, 2020 at 12:31 pm
PhD Title: A Mixed Method Study: Exploring the Perceptions of Cyberbullying and Cyber Aggression in Adolescents and Emerging Adults Description: At present, there are conflicting views as to whether ...
via Bing News