Improving Arabic Stemmer: ISRI Stemmer

Stemmer is used in several types of applications such as Text Mining, Information Retrieval (IR), and Natural Language Processing (NLP). Stemmer is a step used to process text data. The main task in the stemmer is to return the word-formation to the basic word (root or stem). ISRI Stemmer is one of the Arabic stemmers contained in the NLTK package. This study improves the weakness of the ISRI stemmer in processing words consisting of two letters. From the results of the experiment, these improvements increased the stemmer yield by 7.3%.