Microblog user suicide risk detection method and device

Abstract

Embodiments of the invention provide a microblog user suicide risk detection method and a microblog user suicide risk detection device. The method comprises the steps of obtaining a suicide field wordvector of each microblog; processing the suicide field word vector of each microblog by using an LSTM model and an attention mechanism to obtain a text representation matrix of each microblog; splicing the text representation matrix and the image representation matrix of each microblog into a microblog representation matrix of each microblog; processing the microblog representation matrixes of the plurality of microblogs by using an LSTM model and an attention mechanism to obtain suicide risk probability representation matrixes of microblog users; and obtaining the suicide risk probability ofthe microblog user according to the suicide risk representation matrix of the microblog user and the microblog social behavior information matrix of the microblog user. According to the embodiment ofthe invention, the implicit suicide tendency expression in the microblog can be better understood based on the suicide field word vector, the neural network model and the attention mechanism. Therefore, the potential microblog suicide risk can be conveniently detected from the daily microblog.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for detecting suicide risk of microblog users. Background technique [0002] According to data released by the World Health Organization, more than 800,000 people die by suicide every year in the world, an average of one every 40 seconds. In the field of psychology, rapid and accurate detection and prevention of suicide has become an important task. [0003] Traditional suicide risk detection methods generally require subjects to fill out a questionnaire or accept an interview. However, these methods only work for a small group of people, especially for people who tend to hide their feelings after trauma and refuse to seek help from others. [0004] Recently, due to the large-scale, low-cost, and open advantages of social media (such as forums and microblogs), researchers have been able to overcome previous limitations and detect suicidal ideation in indiv...

AI Technical Summary

Problems solved by technology

Although there have been some related works using social media data for user suicide risk detection, the effects of these works are limited to some extent due to users' implicit and unauthentic expressions.

Images