TanmoyGG/Dhaka_Tribune-Scraping-and-Classification-XGBoost

An end-to-end R pipeline for scraping, processing, and classifying Dhaka Tribune news articles. Achieves 94% accuracy using Tidymodels and XGBoost, featuring automated text summarization and smart feature selection.

语言：R · GitHub 星标：4 · Fork：0

话题：nlp · r-language · tidymodels · web-scraping · xgboost-classifier

在 GitHub 上查看原仓库