IEICE TRANSACTIONS on Information
Machine Learning-Based Approach for Depression Detection in Twitter Using Content and Activity Features
Summary :
Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.8 pp.1825-1832
- Publication Date
- 2020/08/01
- Publicized
- 2020/04/24
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020EDP7023
- Type of Manuscript
- PAPER
- Category
- Data Engineering, Web Information Systems
Authors
Hatoon S. ALSAGRI
Al Imam Mohammad Ibn Saud Islamic University (IMSIU)
Mourad YKHLEF
King Saud University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hatoon S. ALSAGRI, Mourad YKHLEF, "Machine Learning-Based Approach for Depression Detection in Twitter Using Content and Activity Features" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 8, pp. 1825-1832, August 2020, doi: 10.1587/transinf.2020EDP7023.
Abstract: Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7023/_p
Copy
@ARTICLE{e103-d_8_1825,
author={Hatoon S. ALSAGRI, Mourad YKHLEF, },
journal={IEICE TRANSACTIONS on Information},
title={Machine Learning-Based Approach for Depression Detection in Twitter Using Content and Activity Features},
year={2020},
volume={E103-D},
number={8},
pages={1825-1832},
abstract={Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.},
keywords={},
doi={10.1587/transinf.2020EDP7023},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Machine Learning-Based Approach for Depression Detection in Twitter Using Content and Activity Features
T2 - IEICE TRANSACTIONS on Information
SP - 1825
EP - 1832
AU - Hatoon S. ALSAGRI
AU - Mourad YKHLEF
PY - 2020
DO - 10.1587/transinf.2020EDP7023
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2020
AB - Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.
ER -
English
