Tokan, Thomas Boris Asalodan
Unknown Affiliation

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

Found 1 Documents
Search

Perbandingan Metode Naïve Bayes dan K-Nearest Neighbor Terhadap Sentimen Analisis Pinjaman Online Siki, Yovinia Carmeneja Hoar; Tokan, Thomas Boris Asalodan; Manehat, Donatus Joseph; Ngaga, Emerensiana; Mau, Sisilia Daeng Bakka
Jurnal Media Informatika Vol. 6 No. 3 (2025): Jurnal Media Informatika
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i3.5687

Abstract

This study aims to understand the public opinion in Indonesia regarding the existence of online loans. Online loans are a type of banking service through technology known as the Financial Technology (FinTech) Industry. According to a report by the Financial Services Authority, in August 2023, more than 13.37 million accounts were using this service. Online loan services are considered to provide convenience and comfort for consumers. However, many harmful cases have emerged, such as extremely high interest rates and aggressive debt collection practices that have caused public concern. Therefore, a sentiment analysis is conducted to understand public opinions, which can serve as a reference for online loan service providers and operators. By using 11,288 Indonesian-language tweets, the public opinion on online loans is analyzed. The study employs two sentiment analysis methods: Naïve Bayes and K-Nearest Neighbor. The results of the study show that the sentiment toward online loans is 62.29% negative, 33.19% neutral, and 5.52% positive. The results also indicate that the Naïve Bayes method has slightly higher accuracy (67%) compared to the K-Nearest Neighbor method (63%). It is hoped that this sentiment will have a positive impact on online loan service providers and operators.