Religious Named Entity Identification for Amharic Language Using Machine Learning

ct   Religious Named Entity Identification (RNEI) plays a crucial role in understanding and classifying religious names in text. This study employs five machine learning models— Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), and Logistic Regression (LR)—to classify names into three categories: Christian, Muslim, and Local names. The dataset consists of 3,233 names collected from various religious sources, including the Bible, Quran, Social Media, and local records. The preprocessing phase involved text normalization, tokenization, and label encoding to prepare the data for training. The models were trained and evaluated based on key performance metrics such as accuracy, precision, recall, and F1-score. The results indicate that the Random Forest model outperforms the others with the highest classification accuracy, followed by SVM and Logistic Regression. KNN and Decision Tree showed comparatively lower performance. The study highlights that ensemble learning techniques, such as Random Forest, significantly enhance classification performance for religious named entity identification. The findings demonstrate the effectiveness of machine learning in automating and improving religious name classification.