Implementation of Naïve Bayes Algorithm for Classification of Mental Health of Social Media Users

Authors

    Aditiya Hermawan( 1 )

    (1) Universitas Buddhi Dharma

DOI:


https://doi.org/10.32877/bt.v4i2.282

Keywords:


Naïve Bayes, Classification, Mental Health, Social Media

Abstract

Social media has become a human need to interact in everyday life. Apart from being a means of communication, social media also has the additional function of exchanging information on the internet in various forms including writing, images and videos. One of the social media that has many users is Instagram, where Instagram offers information sharing features in the form of images, photos and short videos. The purpose of this feature is for users to express themselves and attract the attention of others, thereby creating feelings of happiness and increasing self-confidence. In addition to positive impacts, there are also negative impacts on users, for example excessive use that causes addiction so that it can cause mental health disorders. Mental health needs to be handled properly so that it does not continue to get worse, but there are several obstacles in seeing a psychiatrist in mental health, including limited access and also negative stigma if someone sees a psychiatrist. Therefore, a tool is needed that can be an early indication in knowing the level of mental agitation, especially in the use of Instagram. Classification in data mining can help provide initial information on a person's condition in his mental health. The Naïve Bayes algorithm provides an accuracy rate of 92.5% in classifying mental health on data sets that have been clustered. Good accuracy can help social media users know their mental health condition.

Downloads

Download data is not yet available.

References

W. A. Social, “Digital 2020?: Global Digital Overview,” 2020.

B. D. Atmoko, Instagram Handbook Tips Fotografi Ponsel. Jakarta: Media Kita, 2012.

A. Macmillan, “Why Instagram Is the Worst Social Media for Mental Health,” 2017. [Online]. Available:

https://time.com/4793331/instagram-social-media-mental-health/.

Royal Society For Public Health, “Status of Mind,” 2017. [Online]. Available: https://www.rsph.org.uk/ourwork/campaigns/status-of-mind.html.

World Health Organization, “Mental Disorders,” 2018. [Online]. Available: https://www.who.int/en/newsroom/fact-sheets/detail/mental-disorders.

S. Kemp, “Digital 2020: Global Digital Overview,” 2019. [Online]. Available:

https://datareportal.com/reports/digital-2019-global-digital-overview.

Suyanto, Data Mining untuk Klasifikasi dan Klasterisasi Data. Bandung: Informatika, 2017.

J. Han and M. Kamber, Data Mining: Concepts and Techniques. San Francisco: Elsevier Inc., 2006.

X. Wu and V. Kumar, The Top Ten Algorithms in Data Mining. Taylor & Francis Group, LLC, 2009. DOI: https://doi.org/10.1201/9781420089653

M. Bramer, Principles of Data Mining. London: Springer, 2007.

B. Bukhori, “Hubungan Kebermaknaan Hidup dan Dukungan Sosial Keluarga dengan Kesehatan Mental

Narapidana,” J. Addin, vol. 4, 2012.

Hasneli, Kesehatan Mental dalam Pandangan Islam. Padang: Haifa Press, 2014.

A. Hakim, Hipnoterapi?: Cara Tepat dan Cepat Mengatasi Stres, Fobia, Trauma, dan Gangguan Mental

Lainnya. Jakarta: Visimedia, 2010.

R. T. Vulandari, “Pengelompokan Tingkat Keamanan Wilayah Jawa Tengah Berdasarkan Indeks Kejahatan

dan Jumlah Pos Keamanan dengan Metode Klastering K-Means,” J. Ilm. SINUS, vol. 14, no. 2, 2016.

N. A. Mondoano, R. Mayasari, and F. Gunawan, “Instagram dan Kesehatan Mental pada Mahasiswa Institut

Agama Islam Negeri Kendari,” ANALITIKA, vol. 10, no. 2, p. 104, Dec. 2018. DOI: https://doi.org/10.31289/analitika.v10i2.2034

Downloads

Published

2021-12-30

How to Cite

[1]
A. Hermawan, “Implementation of Naïve Bayes Algorithm for Classification of Mental Health of Social Media Users”, bit-Tech, vol. 4, no. 2, pp. 61–70, Dec. 2021.

Issue

Section

Articles
DOI : https://doi.org/10.32877/bt.v4i2.282
Abstract views: 407 / PDF downloads: 416