Ensemble hybrid learning methods for automated depression detection
Changes in human lifestyle have led to an increase in the number of people suffering from depression over the past century. Although in recent years, rates of diagnosing mental illness have improved, many cases remain undetected. Automated detection methods can help identify depressed or individuals...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/163180 |
| _version_ | 1824456678032015360 |
|---|---|
| author | Ansari, Luna Ji, Shaoxiong Chen, Qian Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Ansari, Luna Ji, Shaoxiong Chen, Qian Cambria, Erik |
| author_sort | Ansari, Luna |
| collection | NTU |
| description | Changes in human lifestyle have led to an increase in the number of people suffering from depression over the past century. Although in recent years, rates of diagnosing mental illness have improved, many cases remain undetected. Automated detection methods can help identify depressed or individuals at risk. An understanding of depression detection requires effective feature representation and analysis of language use. In this article, text classifiers are trained for depression detection. The key objective is to improve depression detection performance by examining and comparing two sets of methods: hybrid and ensemble. The results show that ensemble models outperform the hybrid model classification results. The strength and effectiveness of the combined features demonstrate that better performance can be achieved by multiple feature combinations and proper feature selection. |
| first_indexed | 2025-02-19T03:57:55Z |
| format | Journal Article |
| id | ntu-10356/163180 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:57:55Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1631802022-11-28T05:01:41Z Ensemble hybrid learning methods for automated depression detection Ansari, Luna Ji, Shaoxiong Chen, Qian Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Feature Extraction Depression Changes in human lifestyle have led to an increase in the number of people suffering from depression over the past century. Although in recent years, rates of diagnosing mental illness have improved, many cases remain undetected. Automated detection methods can help identify depressed or individuals at risk. An understanding of depression detection requires effective feature representation and analysis of language use. In this article, text classifiers are trained for depression detection. The key objective is to improve depression detection performance by examining and comparing two sets of methods: hybrid and ensemble. The results show that ensemble models outperform the hybrid model classification results. The strength and effectiveness of the combined features demonstrate that better performance can be achieved by multiple feature combinations and proper feature selection. Published version 2022-11-28T05:01:41Z 2022-11-28T05:01:41Z 2022 Journal Article Ansari, L., Ji, S., Chen, Q. & Cambria, E. (2022). Ensemble hybrid learning methods for automated depression detection. IEEE Transactions On Computational Social Systems, 1-9. https://dx.doi.org/10.1109/TCSS.2022.3154442 2329-924X https://hdl.handle.net/10356/163180 10.1109/TCSS.2022.3154442 2-s2.0-85126518751 1 9 en IEEE Transactions on Computational Social Systems © 2022 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. application/pdf |
| spellingShingle | Engineering::Computer science and engineering Feature Extraction Depression Ansari, Luna Ji, Shaoxiong Chen, Qian Cambria, Erik Ensemble hybrid learning methods for automated depression detection |
| title | Ensemble hybrid learning methods for automated depression detection |
| title_full | Ensemble hybrid learning methods for automated depression detection |
| title_fullStr | Ensemble hybrid learning methods for automated depression detection |
| title_full_unstemmed | Ensemble hybrid learning methods for automated depression detection |
| title_short | Ensemble hybrid learning methods for automated depression detection |
| title_sort | ensemble hybrid learning methods for automated depression detection |
| topic | Engineering::Computer science and engineering Feature Extraction Depression |
| url | https://hdl.handle.net/10356/163180 |
| work_keys_str_mv | AT ansariluna ensemblehybridlearningmethodsforautomateddepressiondetection AT jishaoxiong ensemblehybridlearningmethodsforautomateddepressiondetection AT chenqian ensemblehybridlearningmethodsforautomateddepressiondetection AT cambriaerik ensemblehybridlearningmethodsforautomateddepressiondetection |