Method and device for detecting suicide risk of microblog users

Abstract

The embodiment of the present invention provides a method and device for detecting the suicide risk of microblog users. The method includes: obtaining the suicide field word vector of each microblog; using the LSTM model and the attention mechanism to process the suicide field word vector of each microblog , to obtain the text representation matrix of each microblog; splicing the text representation matrix and image representation matrix of each microblog into a microblog representation matrix of each microblog; The microblog representation matrix is ​​processed to obtain the suicide risk probability representation matrix of the microblog users; according to the suicide risk representation matrix of the microblog users and the microblog social behavior information matrix of the microblog users, the suicide risk probability of the microblog users is obtained. The embodiments of the present invention can better understand the expression of implicit suicide tendency in microblogs based on word vectors in the field of suicide, neural network models and attention mechanisms, thereby facilitating the detection of potential suicide risks in microblogs from daily microblogs.

Description

Technical field [0001] The present invention relates to computer technologies, and particularly to a micro-blog user detection method and the risk of suicide apparatus. Background technique [0002] According to the World Health Organization released data show that each year there are more than 80 million people die by suicide in the world, with an average every 40 seconds a. In the field of psychology, fast and accurate detection and prevention of suicide has become an important task. [0003] Traditional methods generally require the detection of suicide risk subjects fill out a questionnaire or accept an interview. However, these methods apply only to a small group of people, especially for those who are traumatized after often hide their feelings and refuse to seek the help of others, these methods can not play a role. [0004] Recently, social media (such as forums and microblogging) with large-scale, low-cost and open advantage that enables researchers to overcome the limit...

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