Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model
Depression is a global mental health problem, the worst cases of which can lead to self-injury or suicide. An automatic depression detection system is of great help in facilitating clinical diagnosis and early intervention of depression. In this work, we propose a new automatic depression detection...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/23/8701 |
| _version_ | 1827700777162899456 |
|---|---|
| author | Lin Lin Xuri Chen Ying Shen Lin Zhang |
| author_facet | Lin Lin Xuri Chen Ying Shen Lin Zhang |
| author_sort | Lin Lin |
| collection | DOAJ |
| description | Depression is a global mental health problem, the worst cases of which can lead to self-injury or suicide. An automatic depression detection system is of great help in facilitating clinical diagnosis and early intervention of depression. In this work, we propose a new automatic depression detection method utilizing speech signals and linguistic content from patient interviews. Specifically, the proposed method consists of three components, which include a Bidirectional Long Short-Term Memory (BiLSTM) network with an attention layer to deal with linguistic content, a One-Dimensional Convolutional Neural Network (1D CNN) to deal with speech signals, and a fully connected network integrating the outputs of the previous two models to assess the depressive state. Evaluated on two publicly available datasets, our method achieves state-of-the-art performance compared with the existing methods. In addition, our method utilizes audio and text features simultaneously. Therefore, it can get rid of the misleading information provided by the patients. As a conclusion, our method can automatically evaluate the depression state and does not require an expert to conduct the psychological evaluation on site. Our method greatly improves the detection accuracy, as well as the efficiency. |
| first_indexed | 2024-03-10T14:18:44Z |
| format | Article |
| id | doaj.art-b6431473e67a4bdcb88764d76fe056c5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:18:44Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b6431473e67a4bdcb88764d76fe056c52023-11-20T23:32:50ZengMDPI AGApplied Sciences2076-34172020-12-011023870110.3390/app10238701Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based ModelLin Lin0Xuri Chen1Ying Shen2Lin Zhang3School of Software Engineering, Tongji University, Shanghai 201804, ChinaSchool of Software Engineering, Tongji University, Shanghai 201804, ChinaSchool of Software Engineering, Tongji University, Shanghai 201804, ChinaSchool of Software Engineering, Tongji University, Shanghai 201804, ChinaDepression is a global mental health problem, the worst cases of which can lead to self-injury or suicide. An automatic depression detection system is of great help in facilitating clinical diagnosis and early intervention of depression. In this work, we propose a new automatic depression detection method utilizing speech signals and linguistic content from patient interviews. Specifically, the proposed method consists of three components, which include a Bidirectional Long Short-Term Memory (BiLSTM) network with an attention layer to deal with linguistic content, a One-Dimensional Convolutional Neural Network (1D CNN) to deal with speech signals, and a fully connected network integrating the outputs of the previous two models to assess the depressive state. Evaluated on two publicly available datasets, our method achieves state-of-the-art performance compared with the existing methods. In addition, our method utilizes audio and text features simultaneously. Therefore, it can get rid of the misleading information provided by the patients. As a conclusion, our method can automatically evaluate the depression state and does not require an expert to conduct the psychological evaluation on site. Our method greatly improves the detection accuracy, as well as the efficiency.https://www.mdpi.com/2076-3417/10/23/8701automatic depression detectionmulti-modal fusiondeep learningBiLSTM1D-CNN |
| spellingShingle | Lin Lin Xuri Chen Ying Shen Lin Zhang Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model Applied Sciences automatic depression detection multi-modal fusion deep learning BiLSTM 1D-CNN |
| title | Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model |
| title_full | Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model |
| title_fullStr | Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model |
| title_full_unstemmed | Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model |
| title_short | Towards Automatic Depression Detection: A BiLSTM/1D CNN-Based Model |
| title_sort | towards automatic depression detection a bilstm 1d cnn based model |
| topic | automatic depression detection multi-modal fusion deep learning BiLSTM 1D-CNN |
| url | https://www.mdpi.com/2076-3417/10/23/8701 |
| work_keys_str_mv | AT linlin towardsautomaticdepressiondetectionabilstm1dcnnbasedmodel AT xurichen towardsautomaticdepressiondetectionabilstm1dcnnbasedmodel AT yingshen towardsautomaticdepressiondetectionabilstm1dcnnbasedmodel AT linzhang towardsautomaticdepressiondetectionabilstm1dcnnbasedmodel |