Mental Health Status Recognition Based on Bidirectional Long Short Term Memory with Hierarchical Attention Model

In recent years, mental health disorders have become a serious global issue, impacting individuals across the world. It is essential to accurately recognize the mental health issues for effective treatment still conventional diagnostic methods, such as clinician estimations and surveys, have limitations such as time-consuming, and inaccessible for effective interpretation. Therefore, the rapid improvement of deep learning facilitates to provide scalable and data-driven approach to mental health assessment. This approach suggests a novel approach using combination of effective hybrid deep learning models. Initially the data is collected from the dataset psychinfo which is further processed using data cleaning and normalization. Then, the processed data is fed into a transformer model namely T5 which generates and extracts optimal attributes and in the end recognizes the key parameters of mental health illness recognition using a robust hybrid model namely Bidirectional Long Short Term Memory (Bi-LSTM) - Hierarchical Attention Model (HAN). Hence, the proposed method is evaluated by comparing with existing methods such as LSTM and has acquired higher results with an accuracy of 98.63%.

I. Introduction

In recent years, mental health issues was a significant global concern, which was affecting millions of people and imposing substantial burdens on individuals, communities, and healthcare systems [1]. Many physical health conditions are easily diagnosed through measurable biomarkers, but mental health conditions are often less visible and harder to assess accurately. Mental health is a complex and multifaceted field, which is influenced through wide array of factors, including genetic, environmental, and social elements [2]. People experience mental health conditions in diverse ways, and their symptoms manifest differently depending on individual personality, cultural background, and situational factors. The lack of clear standards for interpreting behavioral data and physiological markers in the context of mental health were leads to inconsistent and inaccurate assessments, which are posing various challenges in this field [3]. Consequently, there was rising interest in utilizing technology and data-driven methods to enhance mental health assessments. These approaches aim to analyze patterns in behavior, speech, physiological signals, and other observable indicators to offer a more objective, timely evaluation of an individual's mental health status [4]. Mental health refers to a person's emotional, psychological, and social well-being, which is affecting state of mind while thinking, feeling, and acting. It influences individuals to handle stress, relate to others, and make decisions [5]. Mental health is crucial at every stage of life, from childhood and adolescence through adulthood, and impacted by various factors, including genetics, environment, lifestyle, and life experiences. Mental health issues are predominant worldwide, with various conditions utilizing depression, anxiety, and substance abuse disorders affecting millions of people [6]. Despite its importance, mental health historically overlooked and stigmatized, leading to a lack of awareness, inadequate resources, and insufficient support for strugglers. Mental health disorders are often underdiagnosed and undertreated, and mental health care systems were overburdened.