Depression Detection on Social Media X Using Hybrid Deep Learning CNN-BiGRU with Attention Mechanism and FastText Feature Expansion

Widiarta, I Wayan Abi and Setiawan, Erwin Budi (2025) Depression Detection on Social Media X Using Hybrid Deep Learning CNN-BiGRU with Attention Mechanism and FastText Feature Expansion. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 11 (2). pp. 290-304.

Text 12-Depression Detection on Social Media X Using Hybrid Deep Learning CNN-BiGRU with Attention Mechanism and FastText Feature Expansion.pdf Download (822kB)

Abstract

Depression is a global mental health disorder affecting over 280 million people, with significant challenges in identifying sufferers due to societal stigma. In Indonesia, the National Adolescent Mental Health Survey in 2022 revealed that 17.95 million adolescents experience mental health disorders, with a portion of them suffering from depression. Social media platform X offers an alternative for individuals to share their mental health status anonymously, bypassing societal stigma. This study proposes a hybrid deep learning model combining CNN and BiGRU with an attention mechanism, TF-IDF for feature extraction, and FastText for feature expansion to detect depression in Indonesian tweets. The dataset comprises 50,523 Indonesian tweets, supplemented by a similarity corpus of 151,117 data. To optimize model performance, five experimental scenarios were conducted, focusing on split ratios, n-gram configurations, maximum features, feature expansion, and attention mechanisms. The main contribution of this research is the novel integration of FastText for feature expansion and the attention mechanism within a CNN-BiGRU hybrid model for depression detection. The results demonstrate the effectiveness of this combination, with the BiGRU-ATT-CNN-ATT model achieving an accuracy of 84.40%. However, challenges such as handling noisy, ambiguous social media data and addressing out-of-vocabulary words remain. Future research should explore additional feature expansion techniques, optimization algorithms, and approaches to handle noisy data, improving model robustness for real-world applications in mental health detection.

Item Type:	Artikel Umum
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisi / Prodi:	Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Electrical Engineering (S1-Teknik Elektro)
Depositing User:	M.Eng. Alfian Ma'arif
Date Deposited:	08 Jul 2025 07:28
Last Modified:	08 Jul 2025 07:28
URI:	http://eprints.uad.ac.id/id/eprint/84789

Actions (login required)

View Item