Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal BIMASAKTI
Andriasih, Indra Fitri
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

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

Found 1 Documents
Search

 1 
PENERAPAN ALGORITMA C4.5 PADA ULASAN APLIKASI SHOPEE DI GOOGLE PLAY STORE Andriasih, Indra Fitri; Budianto, Alexius Endy; Walidaroyani, Ainia
Jurnal Fakultas Teknologi Informasi Vol 8 No 2 (2026): BIMASAKTI
Publisher : Prodi Teknik Informatika, Fakultas Sains dan Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21067/bimasakti.v8i2.12763

Abstract

Shopee, as one of the most popular e-commerce platforms in Indonesia, receives numerous user reviews on the Google Play Store. These reviews contain valuable information that can be leveraged to evaluate the quality of the application’s services. This study aims to classify user sentiment using the C4.5 algorithm to assist developers in better understanding user perceptions. The data were collected from the Google Play Store and processed through several stages, including preprocessing (case folding, stopword removal, stemming, word normalization, and sentiment labeling), data transformation using the TF-IDF method, and splitting the dataset into training and testing sets. The C4.5 algorithm was implemented using the DecisionTreeClassifier model with entropy as the criterion. The results indicate that the classification model achieved an accuracy of 83.25% on the test data. The model demonstrated strong performance in classifying positive sentiment, while the classification of negative and neutral sentiments was less optimal due to class imbalance. Therefore, the C4.5 algorithm proves to be effective in classifying user review sentiment, particularly in identifying positive sentiment. These findings can serve as valuable input for Shopee's developers to improve their services based on user feedback.
Co-Authors Budianto, Alexius Endy Walidaroyani, Ainia