Self-Harm Prevention Based On Social Platforms User Data Using Naive Bayes Classifier

Abstract

With the spread of the Internet i.e. World Wide Web, the social networking sites such as Facebook, Twitter, Instagram, Google+ are also in bloom, these social networking sites are not only used by the youth but also been used by the experts to analysis the need, emotion, feeling, comments of the user over the network where user comments directly reflect their state of mind and are widely used in emotion AI. The analysis of the user comments is also used by an analyst to post advertisement over the homepage of a user or make a suggestion of the products, by analysing likes and dislikes of the person. The mental health of a person can also be predicted by analysing the comments made by the user over social media. In this paper, we use naive Bayes classifier for analysing user tweets related to self-harm on Twitter for detection and prevention of self-harm tendencies of the user. The results obtained from the work are promising and can be quite helpful in the development of a system that can be used for prevention of self-harm tendencies in persons using data retrieved from social platforms.