AUTHOR=Ahmed Syed Thouheed , Singh Dollar Konjengbam , Basha Syed Muzamil , Abouel Nasr Emad , Kamrani Ali K. , Aboudaif Mohamed K. 

TITLE=Neural Network Based Mental Depression Identification and Sentiments Classification Technique From Speech Signals: A COVID-19 Focused Pandemic Study

JOURNAL=Frontiers in Public Health

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2021.781827

DOI=10.3389/fpubh.2021.781827

ISSN=2296-2565

ABSTRACT=COVID-19 (SARS-CoV-2) was declared as a global pandemic by World Health Organization (WHO) in February 2020, leading to unpredicted lockdowns of cities, districts, and international travel towards curbing the spread. Various researchers and institutions are focused on multidimensional opportunities and solutions in encountering the COVID-19 pandemic. In this research, the focus is shifted towards the mental health and sentiments validations caused due to the global lockdown across the countries, resulting in a mental disability among the normal individuals. In this paper, a technique is discussed to identify a mental state of an individual by sentiments analysis such as anxiety, depression, and loneliness caused due to isolation and pausing the normal chain of operations. The research is centric with a Neural Network (NN) to resolve and extract the patterns and validate with the threshold trained datasets for decision making. In this technique, 2173 global speech samples are validated, and the resulting accuracy of mental state and sentiments are identified is with 93.5% accuracy in classifying the behavioral patterns of patients suffering from COVID-19 and Pandemic-influenced depression.