A Sentiment Analysis and Unsupervised Learning Approach to Digital Violence Against Women: Monterrey Case

Until a few years ago, Violence Against Women took place both in public and private spaces, but it has now broken into Digital Space, adopting more symbolic expressions. Violence Against Women in Digital Space has recently been legally typified in Mexico, giving the appropriate framework to address it. There have been some important related works from Data Science approaches but mainly on cyberbullying and in detection of language patterns through supervised algorithms. This article seeks to address Violence Against Women in Digital Space in Monterrey, Mexico through Sentiment Analysis and Unsupervised Learning Techniques. The hypothesis is that Sentiment Analysis can associate sentiments to specific subjects that will lead to identify potential Digital Violence Against Women. We will work with Spanish-language text data from microblogging social network, Twitter, datasets.