KLASIFIKASI KESEHATAN MENTAL BERDASARKAN UNGGAHAN MEDIA SOSIAL MENGGUNAKAN TF-IDF DAN XGBOOST

KHOIRUNNISA, YASMIN NUHA and Utami, Alvi Syahrini (2025) KLASIFIKASI KESEHATAN MENTAL BERDASARKAN UNGGAHAN MEDIA SOSIAL MENGGUNAKAN TF-IDF DAN XGBOOST. Undergraduate thesis, Sriwijaya University.

	Image RAMA_55201_09021282126044_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (442kB)
	Text RAMA_55201_09021282126044.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282126044_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55201_09021282126044_0022127804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (496kB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (382kB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (459kB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (226kB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (190kB) | Request a copy
	Text RAMA_55201_09021282126044_0022127804_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (172kB) | Request a copy

Abstract

Mental health is a critical issue in global public health, especially in the digital era where individuals often express their psychological conditions through social media posts. This study aims to develop a multi-class classification model to detect mental health conditions based on social media text using TF-IDF (term frequency–inverse document frequency) for feature extraction and XGBoost (extreme gradient boosting) as the classification algorithm. The dataset used consists of 53,043 English texts categorized into seven mental health classes: Normal, Depression, Suicidal, Anxiety, Stress, Bipolar, and Personality Disorder. The best-performing model, with hyperparameters set to learning rate = 0.2, max depth = 5, and n_estimators = 1000, achieved an accuracy of 78%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	XGBoost, TF-IDF, Klasifikasi Multikelas
Subjects:	P Language and Literature > P Philology. Linguistics > P98-98.5 Computational linguistics. Natural language processing
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Yasmin Nuha Khoirunnisa
Date Deposited:	21 Jul 2025 13:01
Last Modified:	21 Jul 2025 13:01
URI:	http://repository.unsri.ac.id/id/eprint/179373

Actions (login required)

View Item