Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal KOMPUTEK
Hasyimiyyah, Nisrina
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Mechanical Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Analisis Sentimen Ulasan Pembeli pada Toko Skincare Lokal Marketplace Tokopedia menggunakan Metode Sentistrength dan Naïve Bayes Classifier Hasyimiyyah, Nisrina; Mashudi, Irsyad Arif; Arianto, Rakhmat
KOMPUTEK Vol 8, No 2 (2024): Oktober
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/jkt.v8i2.2893

Abstract

Marketplace is an online buying and selling place increasingly in demand by Indonesians. One of the marketplaces with the most visits according to SimilarWeb data is Tokopedia. On Tokopedia, there is a review feature where buyers can send their opinions as criticism or suggestions. Local skincare brands in this research include Avoskin, Azarine, Skin Game, and Somethinc. Buyer reviews listed in each store are triggers for transactions. The purpose of this research is to analyze the sentiment of buyer reviews at local skincare stores on Tokopedia using the SentiStrength method and Naïve Bayes Classifier. Sentiment analysis is carried out to divide buyer review data into negative, neutral, and positive sentiments using a model created with Naïve Bayes Classifier with training and testing data labeled manually using the SentiStrength ID dictionary. Data collection was done using web scraping of 247 data from four stores. The sentiment prediction model uses dataset labeling with SentiStrength ID and a Naïve Bayes Classifier. The process involves the use of complete stopwords without stemming. This model achieved a training accuracy of 94%. However, the testing accuracy only reached 68%. Based on data scraping from 300 reviews, Avoskin has 151 positive reviews, 67 negative reviews, and 8 neutral reviews. Meanwhile, Azarine has 152 positive reviews, 58 negative reviews, and 8 neutral reviews. Skin Game has 186 positive reviews, 54 negative reviews, and 17 neutral reviews. Somethinc has 187 positive reviews, 47 negative reviews, and 20 neutral reviews.
Analisis Sentimen Ulasan Pembeli pada Toko Skincare Lokal Marketplace Tokopedia menggunakan Metode Sentistrength dan Naïve Bayes Classifier Hasyimiyyah, Nisrina; Mashudi, Irsyad Arif; Arianto, Rakhmat
KOMPUTEK Vol. 8 No. 2 (2024): Oktober
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/jkt.v8i2.2893

Abstract

Marketplace is an online buying and selling place increasingly in demand by Indonesians. One of the marketplaces with the most visits according to SimilarWeb data is Tokopedia. On Tokopedia, there is a review feature where buyers can send their opinions as criticism or suggestions. Local skincare brands in this research include Avoskin, Azarine, Skin Game, and Somethinc. Buyer reviews listed in each store are triggers for transactions. The purpose of this research is to analyze the sentiment of buyer reviews at local skincare stores on Tokopedia using the SentiStrength method and Naïve Bayes Classifier. Sentiment analysis is carried out to divide buyer review data into negative, neutral, and positive sentiments using a model created with Naïve Bayes Classifier with training and testing data labeled manually using the SentiStrength ID dictionary. Data collection was done using web scraping of 247 data from four stores. The sentiment prediction model uses dataset labeling with SentiStrength ID and a Naïve Bayes Classifier. The process involves the use of complete stopwords without stemming. This model achieved a training accuracy of 94%. However, the testing accuracy only reached 68%. Based on data scraping from 300 reviews, Avoskin has 151 positive reviews, 67 negative reviews, and 8 neutral reviews. Meanwhile, Azarine has 152 positive reviews, 58 negative reviews, and 8 neutral reviews. Skin Game has 186 positive reviews, 54 negative reviews, and 17 neutral reviews. Somethinc has 187 positive reviews, 47 negative reviews, and 20 neutral reviews.
Co-Authors Irsyad Arif Mashudi Rakhmat Arianto