Jawi Stemmer: Evaluation of Stemmers Based on Strength and Accuracy

Stemmers are important for Information Retrieval and essential for Natural Language Processing. Many researchers have focused on the effect of stemming on document retrieval and measured their stemmers with recall and precision. Applications in text mining (i.e., document indexing and clustering) require great accuracy in index terms. The aim of this paper is to evaluate a Jawi stemmer based on its strength and accuracy. To achieve the result, a control experiment was carried out. Using the results obtained from the experiments conducted in this study, the Jawi stemmer was deemed to be the best stemmer (accuracy = 85.08%), followed by the Abdullah stemmer (accuracy = 81.17%), and the Ahmad stemmer (accuracy = 78.67%).