Algorithm for Simple Sentence Identification in Bahasa Indonesia

A simple sentence identification algorithm of Bahasa Indonesia is proposed in this paper. Sentence identification process is consists of several stages, such as word tokenizing, POS tagging, and sentence structure definition. The proposed algorithm has been tested against 151 sentences obtained from 9 Indonesian documents. Documents consist of ebooks, short stories, online news and journals The test results are also tested by a linguist. The proposed simple sentence structure identification algorithm reaches 83.44% successfulness when compared with the opinion of the linguist.