Harnessing Natural Language Processing for Mental Health Detection in Malay Text: A Review

This paper comprehensively examines mental health detection in the Malay language using natural language processing (NLP) techniques. With global implications, mental health holds significant importance in Malay-speaking regions. NLP, a specialised branch of artificial intelligence, shows promise in deciphering mental health issues from text data. The review begins by exploring traditional NLP approaches like word frequencies, illustrating their role in mental health research. It then focuses on advanced techniques such as embeddings, neural networks, and transformer-based language models. The paper discusses prevalent mental health disorders in Malay-speaking communities and the challenges in their detection. It also highlights distinctive features of Malay mental health datasets crucial for NLP model development. The review delves into studies utilising NLP to analyse mental health content across social media and online forums in Malay contexts. These studies' methods, findings, and limitations are detailed, demonstrating NLP's potential in identifying mental health problems on a larger scale. The review emphasises NLP's role in Malay mental health detection and underscores the need for ongoing research. Leveraging NLP techniques can provide deep insights into the Malay-speaking mental health scenario, facilitating effective interventions and support for individuals with such challenges.