Jurnal Mantik
Vol. 6 No. 3 (2022): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)

Natural Language Processing Analysis Of Frequently Used Words On Indonesia Website Names

Novianti Madhona Faizah (Universitas Tama Jagakarsa)
Luky Fabrianto (Universitas Nusa Mandiri)
Widyat Nurcahyo (Universitas Tama Jagakarsa)
Herlina Trisnawati (Universitas Tama Jagakarsa)



Article Info

Publish Date
19 Nov 2022

Abstract

The increasing of internet use time after time is makes an impact addition of websites, the name of a website must be unique, eye catching and attractive, and in naming a website it should not use spaces, therefore it is often found that the website name consists of several words which are combined. This study aims to determine the most frequently used words on websites in Indonesia. The stages of this research briefly begin with the collection of 10,960 website names, word separation on each website name consisting of several words using Wordninja (one of packages available in Python programming language). The word separation process is carried out in several stages, starting from words containing at least 3 letters to 9 letters. Furthermore, from the word separation stage, ten words that appear most often are sorted. It was found that the word "Indonesia" most often appears at each stage of word separation, which is 139 times. Conclusion of this study is prove that Wordninja were very effective, as evidenced by an accuracy of 97.2%.

Copyrights © 2022






Journal Info

Abbrev

mantik

Publisher

Subject

Computer Science & IT Economics, Econometrics & Finance Languange, Linguistic, Communication & Media

Description

Jurnal Mantik (Manajemen, Teknologi Informatika dan Komunikasi) is a scientific journal in information systems/informati containing the scientific literature on studies of pure and applied research in information systems/information technology,Comptuer Science and management science and public ...