Table 9 Different results while using different parameters.

From: Explainable AI-based suicidal and non-suicidal ideations detection from social media text with enhanced ensemble technique

Study

Aim

Technique

Dataset

Results (F1-core)

Liu et al.3

Suicidal ideation classification

Ensemble learning

Suicidal benchmark dataset

Suicidal = 70%

Non-Suicidal = 84%

Malhotra et al.4

Suicidal ideation classification

XAI-based approach with Transformer

Suicidal benchmark dataset

Suicidal = 86%

Non-Suicidal = 90%

Proposed (our work)

Suicidal ideation classification

XAI-based approach with Ensemble Stacking Classifier

Base Models (SVM,LR,GB,DT)

Meta Model(RF)

Suicidal benchmark dataset

Suicidal = 95.5%

Non-Suicidal = 99%

Back to article page