Text Emotion Classification

Table of Contents

• Introduction
• Features
• Requirements
• Installation
• Usage

Introduction

       Welcome to Text Emotion Classification
      
This project aims to classify text using machine learning algorithm. You can enter a 
sentence of you choice and click on "Classify" and it will label your mood.

Features

* Emotion Detection**: Detect emotions from text data.
* Text Preprocessing**: Preprocess text data for training.
* Model Training**: Train machine learning models for emotion classification.

Requirements

* Python 3.x
* TensorFlow 2.x
* Transformers library

Installation

1. Clone the repository: `git clone https://github.com/Adi-ti09/text-emotion-classification.git`
2. Install requirements: `pip install -r requirements.txt`

Usage

1. Run the script: `python app.py`
2. Follow the prompts to classify text emotions.

Issues you may encounter

* Current version of tranformers is compatible with tf-keras. Please install it to avoid
  exception.
* Ensure to install and the requirements in the same virtual environment.

Acknowledgement

 This project was made possible by the open-source libraries and frameworks used, including:
     1. TensorFlow and its contributors for the machine learning framework
     2. Transformers library and its contributors for the pre-trained models
     3. Python and its community for the programming language
     
 I would also like to acknowledge the datasets used for training and testing, including:
       [www.kaggle.com/datasets/praveengovi/emotions-dataset-for-nlp] for providing the text data for emotion classification. 

Limitations

      While this project has achieved promising results in text emotion classification, there are several limitations to note:
          1. Limited dataset: The project was trained on a limited dataset, which may not be representative of all possible emotions and text styles.
          2. Cultural bias: The dataset and pre-trained models may contain cultural biases, which may affect the accuracy of the emotion classification.
          3. Contextual understanding: The project relies on machine learning algorithms to classify emotions, which may not always understand the nuances of human 
             language and context.
          4. Emotion complexity: Emotions can be complex and multi-faceted, and the project may not be able to capture the full range of human emotions.
          5. Error propagation: The project uses pre-trained models and datasets, which may contain errors or biases that can propagate to the final results.

Contributing

      I welcome contributions to the Text Emotion Classification project.