Abstract: The growing prevalence of mental health issues underscores the need for innovative and effective monitoring systems. Traditional approaches to mental health assessment often rely on self-reported data and clinical evaluations, which can be limited in scope and frequency. Recent advancements in machine learning offer promising alternatives for real-time, scalable, and objective mental health monitoring. Among these advancements, text-based analysis using sentiment analysis and emotion detection has emerged as a powerful tool for understanding and managing mental health. Despite significant progress in sentiment analysis, existing models frequently encounter limitations in addressing the complex and nuanced nature of emotional expression across diverse cultural contexts. Standard models often fail to capture the full spectrum of emotional experiences due to their limited cultural adaptability and inability to handle dynamic emotional states effectively. Natural Language Processing (NLP) refers to a collection of methods for identifying, reading, extracting and untimely transforming large collections of language. In this work, we aim to give an overview of how NLP has successfully been applied thus far in Mental Health Monitoring system. We conduct a literature search on PubMed, Scopus Web of Science and Google Scholar for scientific articles published between 2007and 2024. We use both quantitative and qualitative methods to screen papers and provide insights into the inclusion and exclusion criteria. We outline our approach for article selection and provide an overview of our findings. This is followed by a more detailed insight into selected article. Overall, 2000 articles were screened for the suitability of this review, where we review 69 articles in depth. Finally, we discuss future avenues of research and outline challenges in existing work.
Hemamalini et al. (Thu,) studied this question.