Ridwang, Adriani, Lukman Anas, Nur Akmal, Andi Nasri, Syahbudin
Communication anxiety is a significant challenge within the Deaf community, often hindering social integration and mental well-being. This paper presents a novel approach that integrates deep learning, specifically Long Short-Term Memory (LSTM) networks, with Cognitive Behavioral Therapy (CBT) techniques to address and reduce communication anxiety among individuals with hearing impairments. By leveraging word embedding for natural language processing, the LSTM model is trained to analyze and classify anxiety-related communication patterns from textual data. The integration of CBT principles enables the system to not only identify anxiety triggers but also suggest personalized coping strategies. The proposed model achieves an 87.6% accuracy in detecting communication anxiety, demonstrating its potential as an effective tool for improving mental health support in the Deaf community. The results indicate that combining deep learning with therapeutic techniques offers a promising avenue for reducing communication-related stress and improving overall quality of life for individuals with hearing impairments. © 2025 ICIC International. All rights reserved.
Department of Electrical Engineering, Universitas Muhammadiyah Makassar, Jl., Sultan Alauddin No. 259, Makassar, 90221, Indonesia; Department of Informatics, Universitas Muhammadiyah Makassar, Jl., Sultan Alauddin No. 259, Makassar, 90221, Indonesia; Department of Psychology, Universitas Negeri Makassar, Jl. AP. Pettarani , Sulawesi Selatan, Makassar, 90222, Indonesia; Department of Informatics Engineering, Universitas Handayani Makassar, Jl. Adyaksa Baru No. 1, Pandang, Sulawesi Selatan, 90231, Indonesia; Department of Information System, Universitas Islam Negeri Alauddin Makassar, Jl. Sultan Alauddin No. 63, Gowa, 92113, Indonesia
