Improving Spell Checker Performance for Bahasa Indonesia Using Text Preprocessing Techniques with Deep Learning Models

Abstract

Spell checking capabilities, crucial within the domain of natural language processing, often encounter limitations in the context of Bahasa Indonesia due to data irregularities and the scarcity of high-quality training data. This study aims to enhance spell checker performance through the implementation of various text preprocessing techniques, including case folding, tokenization, stemming, and the removal of stop words. A Convolutional Neural Network (CNN), a deep learning model, was employed in this research to facilitate the overall process. The study utilized data gathered from social media communities, comprising a total of 10,000 entries. This data was divided into two subsets; 80% (8,000 entries) was allocated for training and the remaining 20% (2,000 entries) was designated for testing. A series of tests were conducted on datasets subject to different preprocessing approaches: without case folding, without stop words removal, without stemming, and with all text preprocessing stages implemented. The evaluation metrics employed in this study included accuracy, recall, precision, and the F1 score. The results demonstrated notable improvements in spell checker performance with appropriate text preprocessing. Specifically, the accuracy reached 0.86 for the dataset without stemming, 0.74 for the dataset without stop words removal, 0.7 for the dataset without case folding, and 0.89 for the dataset where all preprocessing stages were applied. These findings suggest that a comprehensive text preprocessing approach, paired with deep learning models, can significantly enhance spell checker performance for Bahasa Indonesia.