Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Informatics and Digital Expert (INDEX)
Therence, Claretty
Unknown Affiliation
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
Beauty Product Recommendation from Customer Reviews Based on Multinomial Naïve Bayes Algorithm Therence, Claretty; Tjen, Jimmy
Informatics and Digital Expert (INDEX) Vol. 7 No. 1 (2025): INDEX, Mei 2025
Publisher : LPPM Universitas Perjuangan Tasikmalaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36423/index.v7i1.2208

Abstract

The cosmetic industry’s increasing dependence on online platforms makes understanding customer sentiment essential for brand success. The study addresses the challenge of understanding customer sentiment regarding concealer brands on the Shopee platform, a critical aspect for brand managers and consumers alike. The problem stems from the vast amount of reviews that can be overwhelming for stakeholders looking to extract actionable insights. To solve this, we applied a Naïve Bayes classification approach with a Bag of Words (BoW) model to analyze a dataset containing 3,920 customer reviews. This dataset was divided into 1,120 training samples and 280 testing samples of each of 10 brands, following an 80:20 ratio. The analysis yields recurring positive and negative sentiment themes, achieving test accuracy of 87.95% and a training accuracy of 94.31%. Findings reveal key consumer preferences and lead to specific product recommendations, such as Mad For Makeup and Luxcrime for high coverage, Guele for lightweight formulas. Additionally, tailored marketing strategies like enhancing packaging and engaging with consumers through social media are suggested. This research provides actionable insights for brand managers, contributing to sentiment analysis literature in the cosmetics sector.
Co-Authors Jimmy Tjen