Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study
Depression is a significant mental health problem and presents a challenge for the machine learning field in the detection of this illness. This study explores automated depression classification, leveraging computational techniques to address this issue. The proposed approach performs spectrogram a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11048471/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849429095505461248 |
|---|---|
| author | Marina Galanina Anna Rekiel Anna BaCzyk Bozena Kostek |
| author_facet | Marina Galanina Anna Rekiel Anna BaCzyk Bozena Kostek |
| author_sort | Marina Galanina |
| collection | DOAJ |
| description | Depression is a significant mental health problem and presents a challenge for the machine learning field in the detection of this illness. This study explores automated depression classification, leveraging computational techniques to address this issue. The proposed approach performs spectrogram analysis and utilizes several machine learning methods, including SVM (Support Vector Machine), Random Forest, MLP (Multilayer Perceptron), and DepAudioNet. The research examines four datasets, namely DAIC-WOZ, EATD Corpus, D-Vlog, and EMU, which vary in terms of linguistic background (English and Chinese), depression classification scales, and gender representation proportions. Feature extraction employs parameters such as formant-related, MFCCs (Mel Frequency Cepstral Coefficients), and jitter parameters. The innovation of this study lies in strategic enhancement, which involves incorporating a gender-specific perspective. This is achieved through the implementation of a tailored feature vector methodology. In most models, this approach led to measurable improvements: SVM improved by 1.43% (p =0.044), MLP-CNN by 7.25% (p =0.008), and Perceptron by 7.39% (p =0.05). Such results underscore the necessity of integrating more personalized methods into the creation of machine learning algorithms for mental diagnostics. |
| format | Article |
| id | doaj-art-be9225d888044cc2bbbd15ea7c84ca93 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-be9225d888044cc2bbbd15ea7c84ca932025-08-20T03:28:28ZengIEEEIEEE Access2169-35362025-01-011311429711430510.1109/ACCESS.2025.358236111048471Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative StudyMarina Galanina0https://orcid.org/0009-0004-4995-7476Anna Rekiel1https://orcid.org/0009-0008-5152-1654Anna BaCzyk2https://orcid.org/0009-0002-8910-8941Bozena Kostek3https://orcid.org/0000-0001-6288-2908Multimedia Systems Department, Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, PolandFaculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, PolandFaculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Gdańsk University of Technology, Gdańsk, PolandDepression is a significant mental health problem and presents a challenge for the machine learning field in the detection of this illness. This study explores automated depression classification, leveraging computational techniques to address this issue. The proposed approach performs spectrogram analysis and utilizes several machine learning methods, including SVM (Support Vector Machine), Random Forest, MLP (Multilayer Perceptron), and DepAudioNet. The research examines four datasets, namely DAIC-WOZ, EATD Corpus, D-Vlog, and EMU, which vary in terms of linguistic background (English and Chinese), depression classification scales, and gender representation proportions. Feature extraction employs parameters such as formant-related, MFCCs (Mel Frequency Cepstral Coefficients), and jitter parameters. The innovation of this study lies in strategic enhancement, which involves incorporating a gender-specific perspective. This is achieved through the implementation of a tailored feature vector methodology. In most models, this approach led to measurable improvements: SVM improved by 1.43% (p =0.044), MLP-CNN by 7.25% (p =0.008), and Perceptron by 7.39% (p =0.05). Such results underscore the necessity of integrating more personalized methods into the creation of machine learning algorithms for mental diagnostics.https://ieeexplore.ieee.org/document/11048471/Mental disordersdepressionspeech processingartificial neural networksmachine learningneural networks |
| spellingShingle | Marina Galanina Anna Rekiel Anna BaCzyk Bozena Kostek Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study IEEE Access Mental disorders depression speech processing artificial neural networks machine learning neural networks |
| title | Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study |
| title_full | Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study |
| title_fullStr | Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study |
| title_full_unstemmed | Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study |
| title_short | Depression Analysis and Detection Using Machine Learning: Incorporating Gender Differences in a Comparative Study |
| title_sort | depression analysis and detection using machine learning incorporating gender differences in a comparative study |
| topic | Mental disorders depression speech processing artificial neural networks machine learning neural networks |
| url | https://ieeexplore.ieee.org/document/11048471/ |
| work_keys_str_mv | AT marinagalanina depressionanalysisanddetectionusingmachinelearningincorporatinggenderdifferencesinacomparativestudy AT annarekiel depressionanalysisanddetectionusingmachinelearningincorporatinggenderdifferencesinacomparativestudy AT annabaczyk depressionanalysisanddetectionusingmachinelearningincorporatinggenderdifferencesinacomparativestudy AT bozenakostek depressionanalysisanddetectionusingmachinelearningincorporatinggenderdifferencesinacomparativestudy |