IRJET - Suicidal Text Detection using Machine Learning

This document presents research on detecting suicidal text using machine learning techniques. The researchers collected Twitter posts and used data preprocessing, word embeddings and a Convolutional Neural Network model to classify tweets as suicidal or non-suicidal. They found that the CNN model achieved the best performance compared to other classifiers. The system could help identify at-risk individuals by analyzing their social media posts and inform organizations to provide support. Future work involves using location data from tweets to better target help to those in need.