Classification of Sundanese Language Used in Social Media: Case Studies on Twitter Users
Ade Sutedi
Sekolah Tinggi Teknologi Garut
Abstract
Language is an element of culture in every nation. The contributions to maintaining this element are to be a good and consistent speaker in daily conversations. Along with the history of the Sundanese tradition, language has an important role to show the existence of Sundanese culture, especially in Banten and West Java. Today, the use of Sundanese language become less frequent due to a competition of regional languages with national languages even with foreign languages. This issue becomes popular in the last decade due to the death of a language issue. The existence of Sundanese language will reflect the strength of the mother tongue uses that becomes characteristic of a region culture, especially for Sundanese language. The objectives of this study are: (1) to classify the Sundanese and not Sundanese language that usually used in social media; (2) to analyze the sentiment of the vocabulary that used in Sundanese language. Classification process takes several types of words from Sundanese vocabulary which divided into three levels: Loma (Ribaldry level), Hormat ka sorangan (Standard level), and Hormat ka batur (Polite level). This process will evaluate the existence of Sundanese language used by users in social media. In this research, the data was taken randomly from Twitter users based on their area, especially in Banten and West Java Provinces.
Keywords: Classification, Sundanese, Death of Language, Social Media, Twitter.
Topic: Computer Science