D₂X: Depression Detection System Through X Using Hybrid Machine Learning
Currently, there is an increasing prevalence of depression among Thai people, often expressed through social media. Unfortunately, many individuals suffering from depression are unaware of their condition. This article introduces a depression detection system through <inline-formula> <tex-m...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10757425/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267921873371136 |
|---|---|
| author | Thara Angskun Suda Tipprasert Atitthan Thippongtorn Jitimon Angskun |
| author_facet | Thara Angskun Suda Tipprasert Atitthan Thippongtorn Jitimon Angskun |
| author_sort | Thara Angskun |
| collection | DOAJ |
| description | Currently, there is an increasing prevalence of depression among Thai people, often expressed through social media. Unfortunately, many individuals suffering from depression are unaware of their condition. This article introduces a depression detection system through <inline-formula> <tex-math notation="LaTeX">$\mathbb {X}$ </tex-math></inline-formula> called <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula>, which utilizes sentiment analysis of <inline-formula> <tex-math notation="LaTeX">$\mathbb {X}$ </tex-math></inline-formula> users’ tweets to predict their level of depression. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> processes various types of tweets, including text messages, emoticons, and images, using a hybrid machine learning approach that combines support vector machine and random forest techniques. The study showed that combining text with emoticons resulted in the highest performance. Additionally, the research revealed that the most crucial feature for predicting levels of depression is the text tweets. Emoticon and image tweets were also found to enhance the effectiveness of detecting depression. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> model, utilizing all types of tweet data, achieved the highest F-measure compared to other machine learning techniques. However, when using only the text messages from tweets, the <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> model showed marginally lower performance than DistilBERT but outperformed other deep learning techniques. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> also had the least model construction and usage time. |
| format | Article |
| id | doaj-art-6e06d8883e234bb0b85d296e1070ce10 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6e06d8883e234bb0b85d296e1070ce102025-08-20T01:53:36ZengIEEEIEEE Access2169-35362024-01-011217282017283110.1109/ACCESS.2024.350224110757425D₂X: Depression Detection System Through X Using Hybrid Machine LearningThara Angskun0Suda Tipprasert1Atitthan Thippongtorn2Jitimon Angskun3https://orcid.org/0000-0002-9373-2723Institute of Digital Arts and Science, Suranaree University of Technology, Nakhon Ratchasima, ThailandFaculty of Business Administration, Rajamangala University of Technology Isan, Nakhon Ratchasima, ThailandSuranaree University of Technology Hospital, Nakhon Ratchasima, ThailandInstitute of Digital Arts and Science, Suranaree University of Technology, Nakhon Ratchasima, ThailandCurrently, there is an increasing prevalence of depression among Thai people, often expressed through social media. Unfortunately, many individuals suffering from depression are unaware of their condition. This article introduces a depression detection system through <inline-formula> <tex-math notation="LaTeX">$\mathbb {X}$ </tex-math></inline-formula> called <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula>, which utilizes sentiment analysis of <inline-formula> <tex-math notation="LaTeX">$\mathbb {X}$ </tex-math></inline-formula> users’ tweets to predict their level of depression. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> processes various types of tweets, including text messages, emoticons, and images, using a hybrid machine learning approach that combines support vector machine and random forest techniques. The study showed that combining text with emoticons resulted in the highest performance. Additionally, the research revealed that the most crucial feature for predicting levels of depression is the text tweets. Emoticon and image tweets were also found to enhance the effectiveness of detecting depression. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> model, utilizing all types of tweet data, achieved the highest F-measure compared to other machine learning techniques. However, when using only the text messages from tweets, the <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> model showed marginally lower performance than DistilBERT but outperformed other deep learning techniques. The <inline-formula> <tex-math notation="LaTeX">$D_{2}\mathbb {X}$ </tex-math></inline-formula> also had the least model construction and usage time.https://ieeexplore.ieee.org/document/10757425/Depression detectionhybrid machine learningsentiment analyticstweet |
| spellingShingle | Thara Angskun Suda Tipprasert Atitthan Thippongtorn Jitimon Angskun D₂X: Depression Detection System Through X Using Hybrid Machine Learning IEEE Access Depression detection hybrid machine learning sentiment analytics tweet |
| title | D₂X: Depression Detection System Through X Using Hybrid Machine Learning |
| title_full | D₂X: Depression Detection System Through X Using Hybrid Machine Learning |
| title_fullStr | D₂X: Depression Detection System Through X Using Hybrid Machine Learning |
| title_full_unstemmed | D₂X: Depression Detection System Through X Using Hybrid Machine Learning |
| title_short | D₂X: Depression Detection System Through X Using Hybrid Machine Learning |
| title_sort | d x2082 x depression detection system through x using hybrid machine learning |
| topic | Depression detection hybrid machine learning sentiment analytics tweet |
| url | https://ieeexplore.ieee.org/document/10757425/ |
| work_keys_str_mv | AT tharaangskun dx2082xdepressiondetectionsystemthroughxusinghybridmachinelearning AT sudatipprasert dx2082xdepressiondetectionsystemthroughxusinghybridmachinelearning AT atitthanthippongtorn dx2082xdepressiondetectionsystemthroughxusinghybridmachinelearning AT jitimonangskun dx2082xdepressiondetectionsystemthroughxusinghybridmachinelearning |