Related Experiment Videos
A cloud-based two-layer text classification framework for mental health screening with sarcasm and emoji-aware
R Thamizh Mani1, Vikram Palimar2, Shashank Singh3
1Department of Forensic Medicine and Toxicology, Kasturba Medical College, Manipal Academy of Higher Education, Manipal, India.
Scientific Reports
|June 23, 2026
Summary
This study introduces a two-layer AI framework using Azure tools to accurately classify mental health concerns in online text. The system achieved high precision and recall, aiding in early detection and screening for mental well-being.
Area of Science:
- Computational linguistics
- Artificial intelligence in healthcare
- Natural language processing for mental health
Background:
- Digital communication platforms facilitate expression of emotions and mental health concerns.
- Traditional sentiment analysis struggles with nuanced, informal language in mental health texts.
- Need for advanced text analytics in mental health screening and triage.
Purpose of the Study:
- To propose a two-layer framework combining Azure Sentiment Analysis and Custom Text Classification.
- To effectively categorize mental health-related text, including specific conditions like Anxiety, Depression, and PTSD.
- To support automated mental health screening and triage applications.
Main Methods:
- Utilized a two-layer framework: Azure Sentiment Analysis followed by Azure Custom Text Classification.
- Classified text into positive, neutral, or negative sentiment.
- Further classified negative sentiment text into predefined mental health categories.
Main Results:
- Achieved an overall Precision, Recall, and F1-score of 96.97% on an 80/20 training/testing split.
- Demonstrated strong class-level performance with F1-scores ranging from 0.94 to 1.000.
- Validated the framework's effectiveness in classifying mental health-related textual content.
Conclusions:
- The proposed framework effectively classifies mental health-related text with high accuracy.
- Cloud-based NLP tools offer a scalable solution for automated mental health text analytics.
- This AI approach serves as a screening tool, not a clinical diagnostic system.
Related Concept Videos
Classification of Illness
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...
Labeling Emotion
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
Classification of Systems-II
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Stereotype Content Model
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
Traits, Mood, and Subjective Wellbeing
Subjective well-being (SWB) refers to an individual's self-evaluation of their overall life satisfaction, happiness, and fulfillment. This multifaceted construct is typically assessed by analyzing the balance of positive and negative emotions alongside perceptions of life satisfaction. Personality traits such as neuroticism and extraversion are strongly associated with variations in SWB, offering critical insights into the underlying mechanisms of emotional well-being.
Neuroticism and Emotional...
Neuroticism and Emotional...