Am I No Good? Towards Detecting Perceived Burdensomeness and Thwarted Belongingness from Suicide Notes

TL;DR

This paper introduces an end-to-end multitask system for detecting perceived burdensomeness and thwarted belongingness from suicide notes, utilizing a new multilingual dataset and leveraging temporal and emotional cues to improve accuracy.

Contribution

It presents a novel multitask detection system for interpersonal risk factors in suicide notes and introduces a new annotated multilingual dataset, CoMCEASE-v2.0.

Findings

Temporal and emotional cues significantly improve detection accuracy

The proposed system outperforms existing approaches on benchmark datasets

New multilingual dataset enhances research in suicide note analysis

Abstract

The World Health Organization (WHO) has emphasized the importance of significantly accelerating suicide prevention efforts to fulfill the United Nations' Sustainable Development Goal (SDG) objective of 2030. In this paper, we present an end-to-end multitask system to address a novel task of detection of two interpersonal risk factors of suicide, Perceived Burdensomeness (PB) and Thwarted Belongingness (TB) from suicide notes. We also introduce a manually translated code-mixed suicide notes corpus, CoMCEASE-v2.0, based on the benchmark CEASE-v2.0 dataset, annotated with temporal orientation, PB and TB labels. We exploit the temporal orientation and emotion information in the suicide notes to boost overall performance. For comprehensive evaluation of our proposed method, we compare it to several state-of-the-art approaches on the existing CEASE-v2.0 dataset and the newly announced CoMCEASE-v2.0 dataset. Empirical evaluation suggests that temporal and emotional information can substantially improve the detection of PB and TB.