Open AccessBuilding the Application to Identify Incorrect Capital Letters Writing in Bahasa Indonesia
Author(s) -
Dani Gunawan,
Andin Vita Amalia,
Ony Naraulita Maringga
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1235/1/012108
Subject(s) - capital (architecture) , set (abstract data type) , computer science , government (linguistics) , natural language processing , artificial intelligence , linguistics , programming language , history , philosophy , archaeology
Ejaan Bahasa Indonesia (EBI) is a set of writing rules in Bahasa Indonesia which is implemented since 2015 according to the government rule Peraturan Kementerian Pendidikan dan Kebudayaan Republik Indonesia Nomor 5 Tahun 2015. This new set of rules replaces previously implemented rules which are known as Ejaan Yang Disempurnakan (EYD). The capital letter rule is one of the elements of EBI. According to the official dictionary of Bahasa Indonesia, the capital letter is a letter which has a bigger size and particular form than the common letter. This research yields an application to identify the incorrect capital letter writing in Bahasa Indonesia based on the user input. The application implements Part of Speech Tagging (POS), Named Entity Recognition (NER), N-Gram and set of rules based on EBI. As the conclusion, the application is able to check 81.57% words that should be written in capital form.