An attention-based hybrid architecture with explainability for depressive social media text detection in Bangla. (1st March 2023)

• Record Type: Journal Article
• Authors: Ghosh, Tapotosh; Banna, Md. Hasan Al; Nahian, Md. Jaber Al; Uddin, Mohammed Nasir; Kaiser, M. Shamim; Mahmud, Mufti
• Is Part Of: Expert systems with applications. Volume 213:Part C(2023)
• Publication Date: 2023-03-01
• Subjects: Depression -- Social media -- Attention -- Mental health -- Suicide; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119007
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Mental health has become a major concern in recent years. Social media have been increasingly used as platforms to gain insight into a person's mental health condition by analysing the posts and comments, which are textual in nature. By analysing these texts, depressive posts can be detected. To facilitate this process, this work presents an attention-based bidirectional Long Short-Term Memory (LSTM)- Convolutional Neural Network (CNN) based model to detect depressive Bangla social media texts, which is lighter and more robust than the conventional models and provides better performance. A dataset containing such Bangla texts was also developed in this work to mitigate the scarcity. Different preprocessing stages were followed, and three embeddings were used in this task. Thanks to the attention mechanism, the proposed model achieved an accuracy of 94.3% with 92.63% of sensitivity and 95.12% of specificity. When tested on other languages, such as English, the proposed model performed remarkably. The robustness and explainability of the proposed model were also discussed in this paper. Additionally, when compared with classical machine learning models, ensemble approaches, transformers, other similar models, and existing architectures, the proposed model outperformed them. Highlights: The proposed method detects depression from Bangla social media texts. The method is based on the bidirectional LSTM and CNN. Attention mechanism was used to improve the performance of the bidirectional LSTM. The proposed method is explainable and outperforms existing methods.