Finding Psychological Instability Using Machine Learning

Introduction

• Channel: JPEG Footage
• Topic: Python project on finding psychological instability using machine learning
• Request: Subscribe and click the bell icon for updates

Project Overview

• Goal: Detect psychological instability
• Method: Using machine learning
• Reference: Details in the base paper

Dataset

• Features:
  • id
  • timestamp
  • age
  • gender
  • country
  • state
  • self-employed
  • (other features mentioned in the base paper)
• Used Features: Select few from the above

Execution Steps

1. Home Screen
   • Title: Finding Psychological Instability Using Machine Learning
2. Login
   • Static credentials: administrator
3. Abstract
   • Displayed as described in the base paper
4. Dataset Upload
   • Preview of dataset features as mentioned earlier
   • Uploaded data includes: timestamp, age, gender, etc.
   • Scroll to view complete upload
5. Train-Test Split
   • Click to train the model
   • Message: Training is finished
6. Prediction Output
   • Features used for prediction:
     • age
     • gender
     • family history
     • self-employed
     • benefits
     • care options
     • anonymity
     • leave
     • work interference

Test Cases

• Normal Person Example

  • age: 31
  • gender: Male
  • family history: Yes
  • self-employed: No
  • benefits: Don't know
  • care option: No
  • anonymity: Don't know
  • leave: Very easy
  • work interference: Never
  • Result: Prediction is normal person

• Mental Disorder Example

  • age: 43
  • gender: Male
  • family history: No
  • self-employed: No
  • benefits: No
  • care option: Don't know
  • anonymity: Don't know
  • leave: Very difficult
  • work interference: Rarely
  • Result: Prediction is mental disorder

Analysis

• Comparison Graphs
  • Comparison of Normal vs Mental Disorder
  • Demographics:
    • Male: 300
    • Female: 500
    • Transgender: 700

Conclusion and Future Work

• Based on the findings in the base paper

Summary

• Project achieved detecting psychological instability using selected features from the dataset and machine learning.

Thank you!