Suicide Classificaction for News Media Using Convolutional Neural\n Network

2021/02/18 by Hugo J. Bello, Nora Palomar-Ciria, Bello, Hugo J. +5
Psychology · #Mental Health via Writing #Suicide and Self-Harm Studies

paper · pdf · doi:10.48550/arxiv.2103.03727

Abstract

Currently, the process of evaluating suicides is highly subjective, which\nlimits the efficacy and accuracy of prevention efforts. Artificial intelligence\n(AI) has emerged as a means of investigating large datasets to identify\npatterns within "big data" that can determine the factors on suicide outcomes.\nHere, we use AI tools to extract the topic from (press and social) media text.\nHowever, news media articles lack of suicide tags. Using tweets with hashtags\nrelated to sucide, we train a neuronal model which identifies if a given text\nhas a suicidade-related contagion. Our results suggest a high level of the\nimpact of mediatic into suicide cases, and a intrinsic thematic relationship of\nsuicide news. These results pave the way to build more interpretable suicide\ndata, which may help to better track, understand its origin, and improve\nprevention strategies.\n

Related

• Detecting potentially harmful and protective suicide-related content on twitter: A machine learning approach
• A Quantitative and Qualitative Analysis of Suicide Ideation Detection using Deep Learning
• Enhanced Suicidal Ideation Detection from Social Media Using a CNN-BiLSTM Hybrid Model
• Detecting Suicidal Ideation in Text with Interpretable Deep Learning: A CNN-BiGRU with Attention Mechanism
• A Picture May Be Worth a Thousand Lives: An Interpretable Artificial Intelligence Strategy for Predictions of Suicide Risk from Social Media Images