Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal INFORMATIKA
Hayati Hayati
Universitas Islam Negeri Sumatera Utara
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 PRODUK SKINCARE PADA PLATFORM SEPHORA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) Aisyah Fadilla Suffi Pohan; Anisa Ninda Cahyani; Retno Anjani; Nazla Windriani; Lutfi Nur Yasin; Amirah Nafiah Zalfa; Hayati Hayati
Informatika: Jurnal Teknik Informatika dan Multimedia Vol. 6 No. 2 (2026): Oktober : JURNAL TEKNIK INFORMATIKA DAN MULTIMEDIA
Publisher : LPPM Politeknik Pratama Kendal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/informatika.v6i2.1958

Abstract

The rapid growth of the skincare industry has sparked a surge in consumer reviews across digital platforms, including Sephora. These digital opinions hold valuable insights into public preferences regarding skincare products; however, the sheer volume of data poses a challenge for manual analysis. This study aims to classify the sentiment of skincare product reviews on Sephora by implementing the Support Vector Machine (SVM) algorithm. A dataset of 49,918 cleaned reviews was utilized following data preprocessing. Sentiment labels were automatically assigned based on ratings: scores of 4–5 were categorized as positive sentiment, while scores of 1–3 were categorized as negative sentiment. Text feature representation was constructed using Term Frequency-Inverse Document Frequency (TF-IDF), limited to the top 5,000 features. The data was subsequently split into training (80%) and testing (20%) sets using a stratified sampling approach. The SVM model employed a linear kernel with a parameter value of C = 1. Testing results demonstrated an accuracy of 90.49% and a macro F1-score of 84.70%. Specifically, the positive class achieved a precision of 92.19%, recall of 96.12%, and F1-score of 94.12%, whereas the negative class recorded a precision of 82.53%, recall of 69.22%, and F1-score of 75.29%. Comparative analysis revealed that SVM outperformed Naive Bayes and Logistic Regression in terms of accuracy and macro F1-score. However, the recall achieved for the negative class indicates a need for further optimization in detecting negative responses. This study confirms the effectiveness of integrating TF-IDF and linear SVM for skincare review sentiment classification, while noting that rating-based annotation has limitations in fully capturing the emotions expressed in the text.
ANALISIS SENTIMEN PENGGUNA APLIKASI ROBLOX MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) Amirah Nafiah Zalfa; Hayati Hayati; Aisyah Fadilla Suffi Pohan; Retno Anjani
Informatika: Jurnal Teknik Informatika dan Multimedia Vol. 6 No. 2 (2026): Oktober : JURNAL TEKNIK INFORMATIKA DAN MULTIMEDIA
Publisher : LPPM Politeknik Pratama Kendal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/informatika.v6i2.1960

Abstract

The expansion of the digital gaming sector has been accompanied by a growing volume of user feedback on application marketplaces, including reviews of Roblox on the Google Play Store. This research examines user sentiment toward Roblox by combining a lexicon-based labeling scheme that uses the Indonesian Sentiment Lexicon (InSet) with a Support Vector Machine (SVM) classifier. A total of 1,000,000 reviews were collected through scraping. The raw corpus was then processed through cleaning, case folding, normalization, tokenization, stopword removal, and duplicate elimination, leaving 772,599 usable reviews. Sentiment labels were assigned with the InSet lexicon, while TF-IDF was applied to convert the text into numerical features before SVM classification. The labeling stage produced 57.58% reviews in the “Good” class and 42.42% in the “Not Good” class. Using a linear kernel, the SVM achieved 94% accuracy, with precision, recall, and F1-score all reaching 0.94. These findings show that the InSet-SVM combination is suitable for categorizing Roblox review sentiment and for describing users’ overall perceptions of the application.
Co-Authors Aisyah Fadilla Suffi Pohan Amirah Nafiah Zalfa Anisa Ninda Cahyani Lutfi Nur Yasin Nazla Windriani Retno Anjani