https://github.com/abhayy-kumar/emotion-detection-system

A machine learning and NLP approach for classifying emotions in text comments.
https://github.com/abhayy-kumar/emotion-detection-system

emotion-detection machine-learning nlp python spacy text-classification

Last synced: about 2 months ago
JSON representation

A machine learning and NLP approach for classifying emotions in text comments.

• Host: GitHub
• URL: https://github.com/abhayy-kumar/emotion-detection-system
• Owner: Abhayy-Kumar
• Created: 2025-03-21T03:03:23.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2025-03-21T03:06:31.000Z (about 2 months ago)
• Last Synced: 2025-03-21T04:22:50.850Z (about 2 months ago)
• Topics: emotion-detection, machine-learning, nlp, python, spacy, text-classification
• Language: Jupyter Notebook
• Homepage:
• Size: 108 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Emotion-Detection-System

A machine learning and Natural Language Processing (NLP) project that classifies emotions in text comments. This project utilizes spaCy for text preprocessing, TF-IDF for feature extraction, and implements both Multinomial Naïve Bayes and Random Forest classifiers to analyze and predict emotions from a Kaggle dataset.

## Overview

The goal of this project is to classify text comments into three emotion categories: **joy**, **fear**, and **anger**. The pipeline involves:

- **Data Acquisition**: Downloading a Kaggle dataset containing text comments and corresponding emotion labels.

- **Exploratory Data Analysis (EDA)**: Understanding dataset structure, distribution of emotions, and sample data.

- **Preprocessing**: Utilizing spaCy for tokenization, lemmatization, and stop word removal.

- **Feature Extraction**: Converting text data into numerical features using TF-IDF vectorization.

- **Model Training & Evaluation**: Implementing Multinomial Naïve Bayes and Random Forest classifiers, followed by evaluating model performance using accuracy scores, classification reports, and confusion matrices.

- **Visualization**: Plotting confusion matrices with Seaborn and Matplotlib to visually interpret model performance.

### Dataset link - https://www.kaggle.com/datasets/abdallahwagih/emotion-dataset