PDF Get rights and content
OriginalPaper | Open access | Published: December 31, 2022

Depression Detection on Twitter Social Media Platform using Bidirectional Long-Short Term Memory

Andre Agasi Simanungkalit, Warih Maharani, Prati Hutari Gani
JINAV: Journal of Information and Visualization, Vol. 3 No. 2 (2022), pp. 190-203 https://doi.org/10.35877/454RI.jinav1503 Published: 2022-12-31
Get Permissions

Abstract

Depression is one of the mental disorders that are often experienced by a person in daily life. Social media platforms is a new thing as an alternative to tell stories and express current feelings by people today. Twitter is one of the social media that is often used to express feelings and opinions through tweets posts, including tweets that contain hate speech which indirectly shows symptoms of depressive disorder through statements uploaded. It also requires modeling that can recognize users with the potential to experience depression so that they can get initial treatment. This can be implemented using the BiLSTM (Bidirectional Long Short-Term Memory) method and the Word2Vec feature. It can be concluded that the dimensional size of the large feature word2vec, LSTM, and Conv1d  layers influenced the model in detecting depression which can be seen in the testing accuracy and F-1 score according to the split data used.

Keywords

Twitter, Mental Illness, BiLSTM, Depression

References (19)

  1. W. Sulistyorin and M. Sabarisman, "DEPRESSION: A PSYCHOLOGICAL REVIEW," Socio Informa: A Study of Social Exploitation and Social Welfare Enterprises, vol. 3, no. 2, pp. 153–164, May 2017, doi: 10.33007.
  2. A. Dirgayunita, "Depression: Its Characteristics, Causes and Handlers," Journal An-nafs: Psychological Studies and Research, vol. 1, no. 1, pp. 1–14, Jun. 2016, doi: 10.33367.
  3. W. Yoeyoen, "InfoDatin-Health-Jiwa," in INFODATIN DATA AND INFORMATION CENTER OF THE MINISTRY OF HEALTH OF THE REPUBLIC OF INDONESIA, 2018, pp. 1–12. Accessed: May 21, 2022. [Online]. Available: https://pusdatin.kemkes.go.id/resources/download/pusdatin/infodatin/InfoDatin-Kesehatan-Jiwa.pdf
  4. L. Mardiana and A. Fa'zia Zi'ni, "SELF-DISCLOSURE OF AUTOBASE ACCOUNT USERS TWITTER @SUBTANYARL," Communication Science Audience, vol. 3, no. 1, pp. 34–54, 2020, doi: 10.33633.
  5. R. Maulina, "Vent Anonymously on Twitter : Come on, Be a Good Listener," Editor of Coil, Dec. 08, 2021. 7. https://kumparan.com/maulina-ratih/curhat-anonim-di-twitter-yuk-jadi-pendengar-yang-baik-1x4AmtvLhqn/2 (accessed May 20, 2022).
  6. C. Sipahutar, A. Poerna, and Nurkinan, "ANONYMOUS CONFIDANT COMMUNICATION EXPERIENCES FOR @18AUTOBASE FOLLOWERS ON TWITTER," Communication Pearl Lens, vol. 4, no. 2, pp. 56–74, Dec. 2020, Accessed: May 20, 2022. [Online]. Available: http://e-journal.sari-mutiara.ac.id/index.php/JLMI/article/view/1414
  7. Auliya Rahman Isnain, Agus Sihabuddin, and Yohanes Suyant, "Bidirectional Long Short Term Memory Method and Word2vec Extraction Approach for Hate Speech Detection," IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 14, no. 2, pp. 169–178, Apr. 2020, doi: 10.22146/ijccs.51743.
  8. Drs. Mardiya, "Knowing Depressive Disorders in Adolescents," Dinas Pemberdayaan Masyarakat Desa dan Kontrol Penduduk dan Keluarga (DPMDPPKB), Dec. 18, 2020. https://pemberdayaan.kulonprogokab.go.id/detil/1308/mengenal-gangguan-depresi-pada-remaja (accessed Jun. 21, 2022).
  9. Cindy Mutia Annur, "Indonesian Twitter Users Enter the Most List in the World, In What Order?," databoks.com, Mar. 22, 2022. https://databoks.katadata.co.id/datapublish/2022/03/23/pengguna-twitter-indonesia-masuk-daftar-terbanyak-di-dunia-urutan-berapa (accessed Jun. 21, 2022).
  10. Sri Kusumadewi and Hepi Wahyuningsih, "MODEL OF GROUP DECISION SUPPORT SYSTEM FOR ASSESSMENT OF DEPRESSIVE, ANXIETY AND STRESS DISORDERS BASED ON DASS-42," Journal of Information Technology and Computer Science (JTIIK), vol. 7, no. 2, pp. 219–228, Feb. 2020, doi: 10.25126.

How to Cite

Simanungkalit, A. A., Maharani, W., & Gani, P. H. (2022). Depression Detection on Twitter Social Media Platform using Bidirectional Long-Short Term Memory. JINAV: Journal of Information and Visualization, 3(2), 190–203. https://doi.org/10.35877/454RI.jinav1503