Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Yessivha Imanuela Claudy
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klasifikasi Dokumen Twitter Untuk Mengetahui Karakter Calon Karyawan Menggunakan Algoritme K-Nearest Neighbor (KNN) Yessivha Imanuela Claudy; Rizal Setya Perdana; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 8 (2018): Agustus 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (724.183 KB)

Abstract

Text mining is the process of mining the text for taking important meaning in it to be able to do the classification. In this study, conducted to know the classification of the characters prospective employees based on the tweets from a company. Tweet that comes from prospective employees will in the process and after that produces characters as one reference in the placement of prospective employees. Then this Employee characters divided into four large groups according the concept of MBTI (Myers-Briggs Type Indicator). Artisan, Guardian, Rational, and Idealist. In addition Artisan, Guardian, Rational and Idealist have characteristics and indicators. After getting the Tweets prospective employees, the next stage will be made classification. This classification method using KNN algorithm. Where, there are 160 tweet data from prospective employees will be grouped MBTI (Myers-Briggs Type Indicator). The data obtained from the company in the form of a tweet from this prospective employees in order to generate the test results are good, then it is divided into two types by a ratio of 50% training data and 50% for the test data. By entering the value of K that is 4 as the value to test. Then get a system accuracy results retrieved from the classification of the characters prospective employees based on their tweets is 66%. These results are the results where there are 53 results of test data and test data results 27 is wrong in the process of testing
Co-Authors M. Ali Fauzi Rizal Setya Perdana