Deep Hierarchical Ensemble Model for Suicide Detection on Imbalanced Social Media Data

Abstract

As a serious worldwide problem, suicide often causes huge and irreversible losses to families and society. Therefore, it is necessary to detect and help individuals with suicidal ideation in time. In recent years, the prosperous development of social media has provided new perspectives on suicide detection, but related research still faces some difficulties, such as data imbalance and expression implicitness. In this paper, we propose a Deep Hierarchical Ensemble model for Suicide Detection (DHE-SD) based on a hierarchical ensemble strategy, and construct a dataset based on Sina Weibo, which contains more than 550 thousand posts from 4521 users. To verify the effectiveness of the model, we also conduct experiments on a public Weibo dataset containing 7329 users' posts. The proposed model achieves the best performance on both the constructed dataset and the public dataset. In addition, in order to make the model applicable to a wider population, we use the proposed sentence-level mask mechanism to delete user posts with strong suicidal ideation. Experiments show that the proposed model can still effectively identify social media users with suicidal ideation even when the performance of the baseline models decrease significantly.

Keywords: China; Sina Weibo; deep neural network; imbalanced data; social media; suicide ideation detection.

Figure 1

The architecture of DHE-SD model.

Figure 2

Hierarchical Ensemble. (a) An example of a classical ensemble method, and (b) an example of a hierarchical ensemble method, where red rectangle represents the base classifier with wrong classification result, and green rectangle represents the base classifier with correct classification result. Taking nine base classifiers as an example, the classical ensemble method cannot give correct prediction results when the number of correct base classifiers is less than half of the total number of classifiers. Through the continuous combination of base classifiers, the hierarchical ensemble method can still give correct prediction results even if the number of correct classifiers is less than half.

Figure 3

An example of sentence-level mask mechanisim. (a) User posts before mask, and (b) User posts after mask.