Loading AI Systems...
Back to Portfolio

News Headline Classifier

NLP app classifies news headlines (SPORTS, CRIME, EDUCATION, COMEDY) with 84% accuracy. Multinomial Naive Bayes + CountVectorizer, Gradio UI, Hugging Face Spaces deploy.

Project Overview

A Natural Language Processing application that automatically classifies news headlines into four categories: SPORTS, CRIME, EDUCATION, and COMEDY. Built using Multinomial Naive Bayes algorithm with CountVectorizer for text preprocessing, the application features a Gradio-based user interface and is deployed on Hugging Face Spaces for easy access.

Dataset / Input Data

Dataset Name / SourceNews Headlines Dataset
FormatText (CSV)
Size / InfoMultiple news headlines across 4 categories

Model / Approach

Algorithm / Model

Multinomial Naive Bayes

Tools / Frameworks

scikit-learnNLTKCountVectorizer

Tech Stack

Python
NLP
Naive Bayes
Gradio
HuggingFace
scikit-learn

Results / Output

Performance Metrics

Accuracy84%
Categories4
AlgorithmMultinomial Naive Bayes

Highlights / Improvements

  • Achieved 84% accuracy on news headline classification
  • Multinomial Naive Bayes with CountVectorizer preprocessing
  • User-friendly Gradio interface
  • Deployed on Hugging Face Spaces
  • Real-time text classification capabilities

Demo / Screenshots