Analyzing the Level of Depression of Twitter Users Using Machine Learning

DOI

10.2991/978-94-6463-445-7_10How to use a DOI?

Keywords

Depression; smartphone use; PHQ-9

Abstract

Depression is a psychological disorder characterized by changes in an individual's feelings, thoughts, and behaviors. According to the American Psychological Association (APA), those who regularly check their smartphones tend to experience higher levels of stress compared to individuals who spend less time with their phones. In the evaluation of depression symptoms, the Patient Health Questionnaire-9 (PHQ-9) can be used. This study describes a method for collecting depression data based on keywords extracted from the PHQ-9 questionnaire, which can indicate the level of depression. Keywords associated with different levels of depression were identified based on the characteristics linked to PHQ-9. These keywords were then utilized to collect data from Twitter, resulting in a dataset of 79,144 entries covering the period from May 28, 2023, to July 1, 2023. The data was subsequently analyzed using a machine learning approach based on Multinomial Naïve Bayes. The analysis revealed that 45,411 Twitter users did not show signs of depression, 2,385 users indicated mild depression, 5,069 users indicated moderate depression, and 3,636 users indicated severe depression. Interestingly, more than 65% of users who indicated experiencing depression, whether mild, moderate, or severe, tended to be more active in participating in social media conversations.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Putri Armaini
AU  - Achmad Maududie
AU  - Priza Pandunata
PY  - 2024
DA  - 2024/06/29
TI  - Analyzing the Level of Depression of Twitter Users Using Machine Learning
BT  - Proceedings of the 2nd International Conference on Neural Networks and Machine Learning 2023 (ICNNML 2023)
PB  - Atlantis Press
SP  - 84
EP  - 93
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-445-7_10
DO  - 10.2991/978-94-6463-445-7_10
ID  - Armaini2024
ER  -