Skip to content

Latest commit

 

History

History
85 lines (49 loc) · 2.31 KB

README.md

File metadata and controls

85 lines (49 loc) · 2.31 KB

Emotion_Intensity_Predictor

The Emotion Intensity Predictor is a Natural Language Processing (NLP) project aimed at predicting the intensity of emotions expressed in textual data. By leveraging advanced NLP techniques, the model aims to provide insights into the strength or magnitude of various emotions conveyed in the text.

Requirements

  • Python 3.x
  • Jupyter Notebook
  • Python Libraries - Numpy, sklearn, tensorflow , pandas , matplotlib , seaborn , nltk

Installation

  1. Clone the Repository
git clone https://github.com/Rishi-Jain2602/Emotion_Intensity_Predictor.git
  1. Install the Project dependencies
pip install -r requirements.txt

Model Training

Knowlege Required

  • Natural Language Processing (NLP)
  • Python Libraries - Numpy, sklearn, tensorflow , pandas , matplotlib , seaborn , nltk
  • Machine Learning Algorithm - SVM , Random Forest classifier , XGB Classifier

Tools

  • Vs code , Codelab

A) Machine Learning Model (Model1)

Sentence Embeddings using Sentence Transformers

Library Used:

Sentence Transformers(Hugging Face)

Model Used

  • SVM - It's accuracy is 77.32%
  • XGB Classifier- It's accuracy is 71.33%
  • Random Forest Classifier is 67.88%

Classification Reports of the models

r1

SVM is giving better result in comparison to other two models

Few Test Cases

test cases1

B) Deep Learning (Model2)

Classification Report

r2

It's accuracy was coming out ot be 84%

Note

  1. Make sure you have Python 3.x installed
  2. It is recommended to use a virtual environment to avoid conflict with other projects.
  3. For deep learning, a laptop with a powerful GPU, a high-performance CPU, at least 8GB of RAM, a fast SSD, and an efficient cooling system is recommended.
  4. If you encounter any issue during installation or usage please contact rishijainai262003@gmail.com or rj1016743@gmail.com