Formal and Non-Formal Indonesian Word Usage Frequency in Twitter Profile Using Non-Formal Affix Rule

Abstract

Indonesian language can be used in a formal or non-formal form. Indonesians generally use both of these forms in communicating on social media. Twitter in Indonesia has quite a lot of users around 22.7 million. This research investigated the frequency of using standard and non-standard words of Indonesians when using Twitter. The research was conducted by utilizing the Non-Formal Affix stemming algorithm to classify words in tweets. Words in tweets are classified into formal, non- formal, and unknown words. The results of the classification in this research indicate that Indonesians use 67.18% of formal words, 12.23% of non-formal words, and the remaining 20.57 of unknown words. The unknown category can be an abbreviation or slang word and a foreign language which is possible to be a non-formal word because it is not in accordance with EYD. Based on this result, Indonesian peoples tweet are dominated by formal word.