Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal INTI Nusa Mandiri
Ramadhinta, Tasya
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
DETEKSI ULASAN FIKTIF SKINCARE BERBAHASA INDONESIA PADA SITUS FEMALE DAILY MENGGUNAKAN METODE SVM Bilqis, Audy Hafiza; Azna, Farizatul; Widdi, Dwi; Hidayat, Nayla Eka; Ramadhinta, Tasya
INTI Nusa Mandiri Vol. 20 No. 2 (2026): INTI Periode Februari 2026
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v20i2.7894

Abstract

The increasing popularity of e-commerce and online review platforms has encouraged consumers to rely more heavily on reviews before purchasing skincare products. However, the proliferation of fake reviews presents a new challenge for consumers in making decisions. This study aims to detect fake reviews of skincare products by applying the Support Vector Machine (SVM) algorithm as the main model. Data was taken from the Female Daily website, which contains a collection of reviews of COSRX skincare products. This study applied text mining and data preprocessing techniques to prepare 8,880 unstructured reviews into a format ready for analysis. The SVM model was used to detect genuine and fake reviews based on linguistic patterns in the text. The test results showed excellent accuracy, with the model accurately predicting 5,900 fake reviews and 2,758 genuine reviews, with an error rate of only around 2.5% of the total data. These findings indicate that SVM is an effective method for detecting fake skincare product reviews and has the potential to be implemented as a decision support tool for consumers and online review platforms.
Co-Authors Azna, Farizatul Bilqis, Audy Hafiza Hidayat, Nayla Eka Widdi, Dwi