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
- Okowa warns on dangers of cyberbullyingon September 17, 2022 at 8:56 pm
Away from the pretences at working for a peaceful election, violence of the 2023 election is already resident in the social media. Cyberbullying is ...
- Bullying Can Cause Inflammation in the Body and Brainon September 16, 2022 at 1:51 pm
Inflammation happens when the body budget tips out of balance in a prolonged, entrenched, chronic way. Barrett uses the example of seeing an authority f ...
- STUDENTS LEARN ABOUT CYBERBULLYINGon September 15, 2022 at 11:57 am
Students at the Carbon Career & Technical Institute recently learned first-hand the law and the consequences of cyberbullying. Carbon County District Attorney Michael Greek and Jack Soberick, ...
- Are you a victim of adult bullying? It’s more common than you’d thinkon September 14, 2022 at 9:04 pm
Because adult bullying is often sneakier and more masked, the person being bullied carries shame and self-doubt — wondering if it’s all ‘in their head’ and they are misinterpreting what is happening,” ...
- Cyberbullying and discipline outlined in local schoolson September 13, 2022 at 3:03 am
It has been weeks since school began and there’s one type of unwanted behavior that can be found in any school district: bullying. “We probably see more student conflict where students aren’t ...
- ‘They can’t get away from it’: Campbell University internet security expert warns of cyberbullying dangerson September 12, 2022 at 8:12 pm
Dr. Amanda Parker says cyberbullying is particularly common among middle school-age students, and it can be difficult to stop.
- Positive Parenting: Local guidance counselor gives tips to id cyberbullyingon September 12, 2022 at 2:34 am
Many kids will be affected by some form of bullying at some point in their lives, but parents have the power to teach them how to prevent cyberbullying and how to handle it if it ...
- "Social Exclusion": The Most Common Form Of Bullying In Schoolson September 11, 2022 at 4:00 am
A new study has found that "social exclusion" is the most common form of bullying in schools, even more so than violence. Bullying is a very serious occurrence, and it can have a large impact on the ...
- Social-Media Content Creation and the Threat of Cyberaggressionon September 8, 2022 at 7:05 am
Psychologist Dorothy Wunmi Grigg refers to such behaviors as cyberaggression—behaviors that intend to give harm using electronic means (Grigg, 2010). Previous research has examined the negative ...
- Cyber violence against women, girls – Renee Laivieraon June 17, 2021 at 10:24 pm
This shows that women and girls are more likely to restrict what they express online for fear of hateful comments, cyberaggression and sexualised cyberbullying. On the other hand, boys tend to ...
via Bing News