NLP Emotion Classification

A Machine Learning project for classifying text into different emotions using Natural Language Processing (NLP) techniques.

📌 Project Overview

This project uses Natural Language Processing and Machine Learning algorithms to identify the emotion expressed in a given text.

The dataset contains text samples along with their corresponding emotion labels. The text is cleaned and transformed into numerical features using Bag of Words (BoW) and TF-IDF techniques.

Different classification models are trained and evaluated to determine their performance on emotion classification.

🚀 Features

• Text preprocessing and cleaning
• Lowercase conversion
• Punctuation removal
• Number removal
• Emoji/non-ASCII character removal
• Stopword removal
• Bag of Words (BoW)
• TF-IDF Vectorization
• Multinomial Naive Bayes
• Logistic Regression
• Model accuracy evaluation

🛠️ Technologies Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• NLTK
• Scikit-learn
• Jupyter Notebook / Google Colab

📂 Dataset

The project uses a text classification dataset imported from kaggle containing two columns:

• text – The input sentence
• emotion – The corresponding emotion label

The dataset is loaded from train.txt using semicolon (;) as the separator.

🔄 NLP Pipeline

Raw Text
    ↓
Lowercase Conversion
    ↓
Punctuation Removal
    ↓
Number Removal
    ↓
Emoji / Non-ASCII Removal
    ↓
Stopword Removal
    ↓
Feature Extraction
    ↓
BoW / TF-IDF
    ↓
Machine Learning Model
    ↓
Emotion Prediction