Emotion Classification Using NLP, Machine Learning & Deep Learning

In this project, I developed a complete NLP pipeline for emotion classification using multiple approaches including Machine Learning, Deep Learning, and Transformer models. - Performed text preprocessing including cleaning, normalization, and stopwords removal using NLTK - Applied TF-IDF vectorization with uni-grams and bi-grams for feature extraction - Built and compared multiple machine learning models (Logistic Regression, SVM) - Developed a Deep Learning model using TensorFlow (Neural Network with multiple layers) - Evaluated model performance using accuracy, classification report, and confusion matrix - Integrated a pre-trained Transformer model using Hugging Face for advanced emotion detection - Created a simple interactive UI using ipywidgets to test predictions with different models Tools & Technologies: Python, Pandas, NumPy, NLTK, Scikit-learn, TensorFlow, Transformers, Matplotlib, Seaborn This project demonstrates my ability to build end-to-end NLP systems and compare different modeling techniques for text classification tasks.