Suicide Classification for News Media Using Convolutional Neural Networks

ABSTRACT

Currently, the process of evaluating suicide is highly subjective, which limits the efficacy and accuracy of prevention efforts. Artificial intelligence (AI) has emerged as a mean of investigating large datasets to identify patterns within ‘big data’ that can determine the factors on suicide outcomes. Here, we used AI tools to extract the topic from (press and social) media texts. However, news media articles lack of suicide tags. Using tweets with hashtags related to suicide, we trained a neuronal model that identifies if a given text has a suicide-related topic. Our results suggest a high level of impact of suicide cases in the media, and an intrinsic thematic relationship of suicide news. These results pave the way to build more interpretable suicide data from the media, which may help to better track, understand its origin, and improve prevention strategies.

Code availability

The source code used in this study is available at https://github.com/news-scrapers and https://github.com/news-scrapers/suicide-subject-classifier-neural-networks-models

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.