Year: 2025
Type: article
Abstract: Depression is a growing global concern, affecting millions of individuals and often going undiagnosed due to stigma and lack of access to mental health professionals. This project aims to develop an AI powered system for early detection of depression using text and speech analysis. The model leverages Natural Language Processing (NLP) to analyze textual input for depressive language patterns and Machine Learning (ML) techniques to detect vocal features associated with depression from speech samples. By integrating sentiment analysis, emotion detection, and acoustic feature extraction, the system can assess linguistic and vocal cues indicative of depressive tendencies. The model will be trained on datasets containing both text-based conversations and speech recordings labeled for depression severity. The goal is to create an assistive tool that can help mental health professionals with early screening and intervention, ultimately improving mental health outcomes.
Authors: Ranjith Durgunala, Tharun Nalamasu, Shruthika Baswa, Vaishnavi Sama
Language: English
Topic: Mental Health via Writing
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4410549847