Machine Learning

Language Detection Using Naive Bayes

A text-classification pipeline that uses TF-IDF features and a Multinomial Naïve Bayes classifier to predict the language of input sentences.

May 2024 Eng. Ameen Qahtan

Project Overview

The notebook loads the “Language Detection.csv” dataset into pandas (10 337 entries with “Text” and “Language” columns), then splits into training and test sets. It vectorizes text using TfidfVectorizer, fits a MultinomialNB model, and evaluates performance via accuracy score, confusion matrix, and classification report .