Skip to content

Latest commit

 

History

History
41 lines (28 loc) · 2.41 KB

README.md

File metadata and controls

41 lines (28 loc) · 2.41 KB
Raw

Identify-Happiness-Index

Problem Statement: Uplifting your Happiness Index infusing Digital Technology Theme : AIML Description: Identify and gather Happiness Index using different sources like human behaviour, life style etc. Detect stress management. Proactively provide recommendation to increase Happiness Index Expectations: Uplifting Happiness

Welcome to the Happiness Index Predictor project! This project aims to predict a person's happiness index and provide recommendations for improving it.

To achieve this, we have implemented multiple machine learning models and developed a full-fledged website to collect and analyze data from the user.

Demo

Happiness.Index.mov

Data Collection

To predict a person's happiness index, we collect the following data from the user:

  1. A questionnaire regarding the happiness index parameters:
    • Real GDP per capita
    • Social support
    • Healthy life expectancy
    • Freedom to make life choices
    • Generosity
    • Perceptions of corruption
  2. A video of the person while solving the questionnaire
  3. An audio input of the person talking about their day and their current emotional state

Data Analysis

We analyze the collected data using the following techniques:

  1. Speech-to-text conversion to extract the sentiments of the person from the audio input
  2. Emotion detection from the video to identify the person's emotional state
  3. Tone detection from the audio input to identify the pitch and emotion of the person's voice
  4. Sentiment analysis of the text extracted from the audio input to identify the person's overall emotional state

Website

We have developed a website using the Flask framework to allow users to easily interact with the project and provide their data for analysis. The website combines both the frontend and backend of the project, allowing users to input their data and receive recommendations for improving their happiness index.

Recommendations

Based on the data collected and analyzed, our machine learning models provide recommendations for improving the user's happiness index. These recommendations may include suggestions for increasing social support, improving healthy habits, or increasing generosity and reducing perceptions of corruption.

We hope that this project will help users to improve their happiness and overall well-being.