Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal Ekonomi Bisnis
Atit Pertiwi
Faculty of Computer Science and Information Technology Gunadarma University
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Social Sciences

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

Found 1 Documents
Search

 1 
ANALYSIS OF OVO APPLICATION SENTIMENT USING LEXICON BASED METHOD AND K-NEAREST NEIGHBOR Sandra Dwi Widiyaningsih; Atit Pertiwi
Jurnal Ilmiah Ekonomi Bisnis Vol 25, No 1 (2020)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1007.104 KB) | DOI: 10.35760/eb.2020.v25i1.2416

Abstract

Money that has a function as a measuring tool, medium of exchange, and payment tools is transformed according to the development of the digital era with the issuance of electronic money. Ovo is an electronic money application in Indonesia. The public can provide a review of the service ovo application on the google play store. Further, the company can see how the responses from the user regarding the product as an evaluation of application performance so that improvements can be made. This requires a system for analyzing reviews by applying sentiment analysis use the R language. The initial stage of sentiment analysis is pre-processing which consists of case folding, cleansing, stopword, slang-word, and stemming. The data classification process is divided into two classes, namely positive and negative classes using the lexicon-based method, the data that has been carried out is then divided into training data and test data that will be used in the training and testing process using the Confusion Matrix. The results of the accuracy of the system using the k-nearest neighbor algorithm of 93.84%. with a positive preposition of 96,29%, negative preposition of 68,75%, positive recall of 96,18%, negative recall of 73,33% and error system of 6,16%.
Co-Authors