International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022
p-ISSN: 2395-0072
www.irjet.net
Detection of Cyberbullying on Social Media using Machine Learning Hanumanthu Venkata Kalyan Sampath1, Mojjada Nandini2, Joga Geetha Manjari3, Boddu Padmasandhya4 1,2,3,4
Final Year B.Tech, CSE, Sanketika Vidya Parishad Engineering College, Visakhapatnam, A.P, India Guided by G.Sandhya, Associate Professor, SVPEC, Visakhapatnam, A.P, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - With the rise of the Internet, the usage of
Bullies have the freedom to damage their classmates' sentiments because they don't have to face them and can hide behind the Internet. Because we everyone, especially youngsters, are continuously connected to the Internet or social media, victims are easily exposed to harassment. The rate of cyberbullying victimisation varies between 10% and 40%. In the United States, almost 43% of teenagers have been bullied on social media at some point. It is our utmost priority to combat cyberbullying is to automatically detect and report bullying texts so that appropriate actions can be taken to avoid potential catastrophes.
social media has increased tremendously, and it has become the most influential networking platform in the twenty-first century. However, increasing social connectivity frequently causes problems. Negative societal effects that add to a handful of disastrous outcomes online harassment, cyberbullying, and other phenomena Online trolling and cybercrime Frequently, cyberbullying leads to severe mental and physical distress, especially in women and children, forcing them to try suicide on occasion. Because of its harmful impact, online abuse attracts attention. Impact on society Many occurrences have occurred recently all across the world. Internet harassment, such as sharing private messages, spreading rumors, etc., and Sexual comments As a result, the detection of bullying texts or messages on social media has grown in popularity. The data we used for our work were collected from the website kaggle.com, which contains a high percentage of bullying content. Electronic databases like Eric, ProQuest, and Google Scholar were used as the data sources. In this work, an approach to detect cyberbullying using machine learning techniques. We evaluated our model on two classifiers SVM and Neural Network, and we used TF-IDF and sentiment analysis algorithms for features extraction. This achieved 92.8% accuracy using Neural Network with 3-grams and 90.3% accuracy using SVM with 4- grams while using TF-IDF and sentiment analysis.
Cyberbullies can be found in work or at school in the classic way. Bullying via cyberspace, on the other hand, stay anonymous, making this type of bullying both effective and harmful. Bullying in schools typically targets children who are physically weak, overweight, unpopular, or disabled, and the bullying occurs during the school day. There is no certain moment when a victim of cyberbullying will be bullied. As a result, the youngsters feel more victimised than usual. Bullying in cyberspace can take the form of uploading photographs or sending depreciate messages. and interactions that can take place in virtual reality, which differs from the reality we are used to. He or she may get a brief break from the bullying, but in cyberbullying, there is no relief from the tension until the victim returns the electronic device. The work of Dooley et al supports the victim's increased sense of powerlessness as a result of cyberbullying (2009). The same victim may predict when he or she will be bullied (for example, in school or on the playground), whereas a victim of cyber bullying has no idea when, when, or how he or she will be bullied (e.g. cell phone, computer), This causes an increased sense of powerlessness. According to recent studies, Online bullying is widespread and is among the most common forms of harassment among adolescents.
Key Words: Cyberbullying, Hate speech, Personal attacks, Machine learning, Feature extraction, analysis, Cybercrime, Neural Networks.
Sentimental
1. INTRODUCTION SOCIAL Media is a collection of web-based programmes that let users to create and share user-generated content, built on the conceptual and technological basis of Web 2.0. People can gain access to a wealth of knowledge, as well as a quick way to communicate. However, social media can have bad consequences, such as cyberbullying, which can affect people's lives, particularly children and teenagers. Cyberbullying is described as aggressive, intentional activities taken against a victim through digital communication methods such as sending messages and making remarks. Cyberbullying on social media, unlike traditional bullying, which mainly occurs at school during face-to-face conversation, can occur anywhere at any time.
© 2022, IRJET
|
Impact Factor value: 7.529
Cyberbullying is an arising societal issue in the digital period. The Cyberbullying Research Centre conducted a civil check of 5700 adolescents in the US and plant that 33.8 of the repliers had been cyberbullied and11.5 had cyberbullied others. While cyberbullying occurs in different online channels and platforms, social networking spots (SNSs) are rich grounds for online bullying. A recent check conducted by Ditch the Marker, an anti-bullying
|
ISO 9001:2008 Certified Journal
|
Page 1067