Text Classification Using CNN

This project demonstrates high-accuracy text classification using a Convolutional Neural Network (CNN). The model achieves 98% accuracy on a labeled dataset, showcasing how deep learning can effectively categorize text data for NLP applications.

Key Features

CNN for NLP – Leverages 1D convolutions to extract meaningful patterns from text.

High Accuracy – Achieves 98% validation accuracy, outperforming traditional ML models.

Preprocessing Pipeline – Includes tokenization, padding, and embedding (Word2Vec/GloVe).

Model Evaluation – Metrics like accuracy, precision, recall, and confusion matrix.

Scalable Architecture – Can be adapted for sentiment analysis, spam detection, or topic labeling.

Technologies Used

Python

TensorFlow/Keras

NLTK/spaCy (text preprocessing)

Scikit-learn (metrics & utilities)

Matplotlib/Seaborn (visualization)