Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195242,
        author = {Dr. MK Jayanthi Kannan and Aviral Mehndiratta},
        title = {Deep Learning Framework for Emotion-Aware Text Classification System for Proactive Mental Health Intervention},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7998-8007},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195242},
        abstract = {Mental health issues such as anxiety and depression have become increasingly common, particularly among students and young adults. Early identification of these conditions is important for promoting timely support and improving overall well-being. This project presents a machine learning–based mental health detection system that analyzes textual input to identify potential signs of anxiety and depression. The system utilizes Natural Language Processing (NLP) techniques to preprocess user-provided text through tokenization, stopword removal, and stemming. Feature extraction is performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method to convert textual data into numerical representations suitable for machine learning models. Multiple classification algorithms were evaluated, and the Decision Tree classifier was selected due to its high accuracy and interpretability. The developed system is implemented as a web- based application using a Flask backend, enabling users to input text and receive real-time predictions regarding their emotional state. In addition to providing prediction results with confidence scores, the system also offers supportive resources such as mental health helplines and guidance. The proposed solution aims to serve as an accessible and non- invasive tool that encourages early mental health awareness and assists users in seeking appropriate support when necessary. Mental health disorders, particularly anxiety and depression, represent a growing global burden, with a significant impact on students and young adults. Early detection remains a critical challenge due to stigma, lack of awareness, and limited access to professional screening. This paper presents a machine learning-based mental health detection system designed to identify potential signs of anxiety and depression from user-generated textual input. The proposed system employs a robust pipeline consisting of Natural Language Processing (NLP) techniques—including tokenization, stopword removal, and stemming—for text preprocessing. Feature extraction is performed using Term Frequency–Inverse Document Frequency (TF-IDF) vectorization to convert textual data into a numerical format suitable for classification.},
        keywords = {Mental Health Detection, Machine Learning, Natural Language Processing, TF-IDF Vectorization, Decision Tree Classifier, Text Classification, Web-Based Application, Anxiety and Depression Detection.},
        month = {March},
        }