A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media
Depression has become one of the most common mental illnesses, and the widespread use of social media provides new ideas for detecting various mental illnesses. The purpose of this study is to use machine learning technology to detect users of depressive patients based on user-shared content and pos...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2021.802821/full |
| _version_ | 1819007681274314752 |
|---|---|
| author | Jingfang Liu Mengshi Shi |
| author_facet | Jingfang Liu Mengshi Shi |
| author_sort | Jingfang Liu |
| collection | DOAJ |
| description | Depression has become one of the most common mental illnesses, and the widespread use of social media provides new ideas for detecting various mental illnesses. The purpose of this study is to use machine learning technology to detect users of depressive patients based on user-shared content and posting behaviors in social media. At present, the existing research mostly uses a single detection method, and the unbalanced class distribution often leads to a low recognition rate. In addition, a large number of irrelevant or redundant features in high-dimensional data sets interfere with the accuracy of recognition. To solve this problem, this paper proposes a hybrid feature selection and stacking ensemble strategy for depression user detection. First, recursive elimination method and extremely randomized trees method are used to calculate feature importance and mutual information value, calculate feature weight vector, and select the optimal feature subset according to the feature weight. Second, naive bayes, k-nearest neighbor, regularized logistic regression and support vector machine are used as base learners, and a simple logistic regression algorithm is used as a combination strategy to build a stacking model. Experimental results show that compared with other machine learning algorithms, the proposed hybrid method, which integrates feature selection and ensemble, has a higher accuracy of 90.27% in identifying online patients. We believe this study will help develop new methods to identify depressed people in social networks, providing guidance for future research. |
| first_indexed | 2024-12-21T00:28:26Z |
| format | Article |
| id | doaj.art-a5ef3baad81c431081d1747a57ea49b5 |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-12-21T00:28:26Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-a5ef3baad81c431081d1747a57ea49b52022-12-21T19:21:56ZengFrontiers Media S.A.Frontiers in Psychology1664-10782022-01-011210.3389/fpsyg.2021.802821802821A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social MediaJingfang LiuMengshi ShiDepression has become one of the most common mental illnesses, and the widespread use of social media provides new ideas for detecting various mental illnesses. The purpose of this study is to use machine learning technology to detect users of depressive patients based on user-shared content and posting behaviors in social media. At present, the existing research mostly uses a single detection method, and the unbalanced class distribution often leads to a low recognition rate. In addition, a large number of irrelevant or redundant features in high-dimensional data sets interfere with the accuracy of recognition. To solve this problem, this paper proposes a hybrid feature selection and stacking ensemble strategy for depression user detection. First, recursive elimination method and extremely randomized trees method are used to calculate feature importance and mutual information value, calculate feature weight vector, and select the optimal feature subset according to the feature weight. Second, naive bayes, k-nearest neighbor, regularized logistic regression and support vector machine are used as base learners, and a simple logistic regression algorithm is used as a combination strategy to build a stacking model. Experimental results show that compared with other machine learning algorithms, the proposed hybrid method, which integrates feature selection and ensemble, has a higher accuracy of 90.27% in identifying online patients. We believe this study will help develop new methods to identify depressed people in social networks, providing guidance for future research.https://www.frontiersin.org/articles/10.3389/fpsyg.2021.802821/fulldepressionmachine learningensemble learningfeature selectionsocial media |
| spellingShingle | Jingfang Liu Mengshi Shi A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media Frontiers in Psychology depression machine learning ensemble learning feature selection social media |
| title | A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media |
| title_full | A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media |
| title_fullStr | A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media |
| title_full_unstemmed | A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media |
| title_short | A Hybrid Feature Selection and Ensemble Approach to Identify Depressed Users in Online Social Media |
| title_sort | hybrid feature selection and ensemble approach to identify depressed users in online social media |
| topic | depression machine learning ensemble learning feature selection social media |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2021.802821/full |
| work_keys_str_mv | AT jingfangliu ahybridfeatureselectionandensembleapproachtoidentifydepressedusersinonlinesocialmedia AT mengshishi ahybridfeatureselectionandensembleapproachtoidentifydepressedusersinonlinesocialmedia AT jingfangliu hybridfeatureselectionandensembleapproachtoidentifydepressedusersinonlinesocialmedia AT mengshishi hybridfeatureselectionandensembleapproachtoidentifydepressedusersinonlinesocialmedia |