Loading [MathJax]/extensions/MathMenu.js
Detecting Cyber Bullying on Twitter using Support Vector Machine | IEEE Conference Publication | IEEE Xplore

Detecting Cyber Bullying on Twitter using Support Vector Machine


Abstract:

On the platform provided by social media, a significant number of young people are subjected to bullying. Cyberbullying is becoming a more widespread problem with the pro...Show More

Abstract:

On the platform provided by social media, a significant number of young people are subjected to bullying. Cyberbullying is becoming a more widespread problem with the proliferation of social networking platforms. To discover word similarities in the tweets that were written by bullies, utilize Machine Learning, and develop a ML model that can do automatic identification of the bullying acts on different social media websites or platforms. Yet, many other methods for detecting bullying on social media have been deployed, however, the majority of these methods are text-based. The goal of this work is to show how software may be developed that can detect bullying in tweets, postings, and other online communications. It has been suggested to use a model that uses machine learning to identify bullying on Twitter. SVM is used in the classification process, whereas NLP is utilized for the processing of the data. Additionally, in order to decide whether or not a tweet constitutes bullying, the Twitter API is used to gather the tweets, which are then loaded into a model.
Date of Conference: 02-04 February 2023
Date Added to IEEE Xplore: 27 March 2023
ISBN Information:
Conference Location: Coimbatore, India

I. Introduction

The word "machine learning" refers to a various collection of computer algorithms that, via the processes of "self-improvement" and "learning from example," may acquire new skills without having to be specifically programmed by a human. Machine learning is a subfield of AI that integrates data analysis with statistical methods in order to make predictions about future outcomes and provide insights that can be put to practical use. The notion that a computer can independently learn from the information to provide exact results is the conceptual breakthrough that led to this achievement [1]. Data mining and Bayesian predictive modeling are two more fields that are strongly connected to machine learning. The machine takes the data that it gets as input and processes it using an algorithm in order to provide replies. One of the most common applications of machine learning is to provide recommendations. All suggestions of movies or series for users with a Netflix account are determined by the user’s viewing history and tailored according to the user’s preferences. IT companies are utilizing unsupervised learning to improve the client experience by making more specialized recommendations.

Contact IEEE to Subscribe

References

References is not available for this document.