About This Model

This machine learning model classifies free‑text documents into one of the 20 Newsgroups categories, such as politics, sports, computers, religion, and more. It uses a TF‑IDF text vectorizer to convert your text into numerical features, and a Linear Support Vector Machine (SVM) to determine the closest matching category.

How the Model Reads Your Input

• Your text is broken into words (tokens).
• Each word is weighted using TF‑IDF (Term Frequency–Inverse Document Frequency).
• The SVM compares your text to thousands of training documents.
• The category with the strongest match becomes the prediction.

There are no numeric fields or fixed ranges — the model accepts any English text up to about 1,000 words.

Enter Text from any Article to Classify

Note: The model works best with inputs under 1,000 words.

Predict Category

How to Interpret the Results

The Predicted Category is the single best match for your text. The Top 3 Most Likely Categories show the closest alternatives based on the SVM’s decision scores.

• Higher scores mean a closer match.
• Scores may be negative — this is normal for SVMs.
• The category with the highest score is the prediction.