Hate Text Finder Using Logistic Regression

Hate Text means a message designed to degrade, intimidate or incite to violence or prejudicial action against a person or group of people based on their race, gender, ethnicity, nationality, religion, political affiliation, language, ability or appearance. Offensive, abusive and profane language on social networks is an issue that governments and tech firms are trying to resolve. Considering the number of Internet users in world and the conflict caused by offensive content involved in posts, there is a need to build post-level inappropriate content filtering. This project uses an logistic regression model for classifying the words as (non) offensive words. This model can assist government enforcing the information and decreases the number of disputes due to aspiration freedom abuse in social media. In this project, we developed a social blog to demonstrate this entire process and it shows good results. We are testing that whether the post contains offensive content or not at the time of posting itself.