Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Rahma Chairunnisa
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 
Analisis Sentimen terhadap Karyawan Dirumahkan pada Media Sosial Twitter menggunakan Fitur N-Gram dan Pembobotan Augmented TF - IDF Probability dengan K-Nearest Neighbour Rahma Chairunnisa; Indriati Indriati; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 4 (2022): April 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sentiment analysis is one of method that is often used to determine the sentiment in a sentence based on its analysis. Sentiment analysis is one of the methods in text mining that uses the process of text preprocessing and then continued the process of word weighting. The case of corona virus or COVID-19 in Indonesia has reached 6 thousand more on Saturday afternoon (18/4/2020). A total of 11 regions in Indonesia apply PSBB with Jakarta as the first city to do it. Many companies finally do layoffs with the employees due to the pandemic corona virus. There are exposed Termination of Employment (PHK), laid off, working part, cutting salaries, and so on. There are some stages in this research, namely preprocessing for processing of documents, and use the features of the unigram and a bigram and by weighting words using the Augmented TF - IDF Probability and will be clarified by using the method of K-Nearest Neighbour. The Data are used as much as 250 training data and 100 test data. The best results obtained from this study with values of K = 3 to unigram, is accuracy worth 0.68, precision worth 0.415, recall worth 0.404, f-measure worth 0.406. And for the value of a bigram that accuracy is worth 0.776, precision is worth 0.591, recall is worth 0.408, f-measure is worth 0.437. The selection term unigram and a bigram is very influential on the results of this study. So that the visible results of each evaluation value that has been done have a considerable difference in value
Co-Authors Indriati Indriati Putra Pandu Adikara