NON-STANDARD WORDS DETECTION SYSTEM IN A TEXT WITH WORD MATCHING METHOD

SURYANI, DES and AMBIYAR, AMBIYAR and HUDA, ASRUL and PILIANG, WILDA SRIHASTUTY HANDAYANI and MELYANTI, RIKA and AYU, FITRI (2021) NON-STANDARD WORDS DETECTION SYSTEM IN A TEXT WITH WORD MATCHING METHOD. Journal of Xi'an Shiyou University, Natural Sciences Edition. ISSN 1673-064X

Text 7. BHD3J (2) (1).pdf - Published Version Download (787kB)

Abstract

Indonesian is the state language which is the official language of the Unitary State of the Republic of Indonesia. The Indonesian language used must be standard or standard Indonesian and by good and correct Indonesian spelling rules. In its implementation in the field, there are still many errors in the standard language in the development of the national culture, science, and technology. An example is found in the use of the wrong standard words in writing scientific essays in Indonesian. This happens because of the lack of mastery of standard vocabulary among writers. In addition, it can also occur due to the habit of people who often pick up the language around them without any filtering process first. The languages that are commonly used are considered correct and are never interested in find�ing out the origin or meaning of the language. In the end, what happened was the use of the wrong Indonesian language was used for generations. Based on the phenomena that occur in society, it is necessary to research to build a non-standard word shortening system using the Python programming language and the Approximate String Matching method. This system will match the words in the non�standard word bag of words (TB) with the abstract text. Abstract data used as samples are abstracts from texts (reports, papers, scientific works) provided that the number of words in the abstract does not exceed 200 words. The results of this study can find and determine the number of non-standard words contained in one or several abstracts and replace them with standard words.

Actions (login required)

View Item