Stress Indicators Dataset for Mental Health Classification

This dataset captures responses from 2,000 students regarding their experiences with stress, health, academics, and emotional well-being. The original dataset was collected via Google Forms survey and later expanded to ensure sufficient sample size for machine learning research. The survey items used a five-point Likert scale (1 = Not at all to 5 = Extremely). All responses have been anonymized to protect participants’ privacy.

The dataset is suitable for:

Stress detection and classification (Eustress vs. Distress).

Analyzing correlations between psychological, academic, and social stressors.

Developing machine learning models for student mental health monitoring.

🔑 Key Features
👤 Demographics

gender: 0 = Male, 1 = Female

age: Numeric (18–22)

🧠 Emotional & Stress Indicators

stress_experience

heartbeat_palpitations

anxiety_tension

sleep_problems

restlessness

irritability

sadness_low_mood

loneliness_isolation

concentration_problems

🩺 Physical & Health Indicators

headaches

health_issues

weight_changes

📚 Academic & Environment Stressors

academic_overload

peer_competition

low_academic_confidence

subject_confidence

academic_conflicts

class_attendance

professor_difficulties

work_environment

home_environment

💬 Social & Relationship Factors

relationship_stress

lack_relaxation_time

🎯 Target Variable

stress_type (encoded):

0 = Distress (Negative Stress)

1 = Eustress (Positive Stress)

2 = Other / Mixed Stress

📂 Dataset File

File: Stress_Dataset_Polished_Encoded.csv

Rows: 2,000

Columns: 26

Missing Values: None

Duplicates: None

Target Variable: stress_type (3 classes)