Logo Lanfrica

brian-analytics/Model-swahili-news-classification

Domaine:

natural language processing

Type de record:

model
Créateur:
bri
HĂ´te:
A machine learning model to classify Swahili news articles into 5 categories # 🗞️ Swahili News Classification A machine learning project that classifies Swahili news articles into 5 categories: Kitaifa, Kimataifa, Biashara, Michezo, and Burudani. ## 📂 Project Files - `swahili_news_classification.ipynb` — Main notebook with full analysis - `submission.csv` — Final predictions for the Zindi competition - `*.png` — Charts and visualisations generated during analysis ## 🛠️ Tools Used - Python, pandas, scikit-learn - TF-IDF Vectorization - Logistic Regression, Naive Bayes, SVM, Random Forest ## 📊 Results Best model: Logistic Regression with TF-IDF (unigrams + bigrams)