Utilization Of Support Vector Machine For Analyzing Women Safety In Indian States

Abstract

  Women from various parts of the world always experience a lot of harassment, starting from stalking, passing vulgar comments, and leading to sexual assault. They still feel like men are eyeing them when they travel or roam outside. To control their paranoia in this unsafe society, we need to manage and handle the potentially detrimental situations that may lead to such unfortunate events.  Twitter gives an excellent feature for women to express their views about what they feel while they travel or go out. We can categorize their opinions by using tweets. Hence by reviewing these classified tweets, we can identify the places which are less safe for women. The main focus of this research paper is to find out the least safe state in our country so that we can educate people in that area to promote the safety of women with the help of social media. That way, we can contribute to making the world a better place to live for women. This paper also focuses on the efficiency analysis of three machine learning algorithms – Naïve Bayes, Random Forest, Support Vector Machine (SVM).