Abstract
Content analysis of messages in social networks, identification of suicidal types
Aejaz, A., Owais, M.Z., & Kalyani, G.
This project describes content analysis of text with to identify suicidal tendencies and types. This article also describes how to make a sentence classifier that uses a neural network created using various libraries created for machine learning in the Python programming language. Attention is paid to the problem of teenage suicide and “groups of death” in social networks, the search for ways to stop the propaganda of suicide among minors. Analysis of existing information about so-called “groups of death” and its distribution on the Internet. Individuals who suffer from suicidal ideation frequently express their views and ideas on social media. Thus, several studies found that people who are contemplating suicide can be identified by analyzing social media posts. However, finding and comprehending patterns of suicidal ideation represent a challenging task. Therefore, it is essential to develop a machine learning system for automated early detection of suicidal ideation or any abrupt changes in a user’s behavior by analyzing his or her posts on social media. The system leverages the Naive Bayes algorithm, which assumes independence between features, to learn the associations between textual content and different suicidal types. The dataset is preprocessed, and features are extracted from the text using techniques such as CountVectorizer. The dataset is then split into training and testing sets for model evaluation.