Stemming Algorithm for Indonesian Signaling Systems (SIBI)

Abstract

The Indonesian Language Sign System (SIBI) is a medium used by deaf people to communicate with the wider community. SIBI is Indonesian that is presented by hand. The sentence structure (morphology) of SIBI is the same as the Indonesian language, SIBI also recognizes the prefix, principal and suffix sign word. This research discusses how to make stemming for SIBI, the algorithm used for stemming is Nazief Adiri. Stemming for SIBI separates input sentences, words through the Text Processing process. Then the word in Stemming so that it can be separated into prefix, main, and suffix words. After stemming, the words obtained in indexing can find the right SIBI, by using ID. Good stemming must pay attention to Indonesian Morphology. The number of words used for this stemming trial is 50 words. By using the Confusion Matrix method found 0.94% accuracy, 93% recall, and 84% precision.