Analyzing the Performance of Naive Bayes, Logistic Regression, SVM and Random Forest for Identifying Hate speech from Twitter Social Media
Disha Sushant Wankhede, Vidya Shrimant Gaikwad, Akshay Manikjade, Nikita Meher, Tejas Atkale, Aishwarya Ghule, Deepika Gujar · 2023
The spread of hate on social media and other platforms is of great concern because it has the implicit to be a serious detriment to society and the country and is disastrous. The development of mass media has led to lower exposure of hate speech and discrimination. detest speech generally refers to a person or group of people predicated on race, color, race, gender, race, religion, etc It's defined as humiliating communication grounded on certain characteristics. The donation of Structure through named images, type of caption and words used in the textbook of ) can explain the causes of virality and what is associated with it. Fake news and hate speech are not the result of the internet age. Fake news and hate have been around since the morning of mortal history, that is, for times- people have fabricated and fabricated all the time. still, the phenomenon of social media has changed how, where and what it's associated with fake news and hate speech. Where lies and culmination formerly appeared on the internet, now fake news and hate speech are taking their place on social media. The thing of the design is to propose results that stoners can use to identify and filter to count hate speech on Twitter. Using colorful bracket styles, we can determine whether tweets are hate speech. We use traditional shadowing algorithms Analogous as Naive Bayes, Logistic Regression, SVM and Random Forest. From data collection, preprocessing, point engineering and type to, we will estimate and give the delicacy and quality of all classifiers and their results in discrimination quests on Twitter..