Publication Search

The rapid growth of e-commerce in Indonesia, particularly the Shopee platform, has generated a large volume of user reviews on the Google Play Store, which can be analyzed to understand consumer sentiment. This study aims to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in binary sentiment classification (positive and negative) on Shopee reviews, as well as to statistically test the significance of their differences using One-Way ANOVA. A total of 400,498 reviews were collected via web scraping, preprocessed through text normalization, tokenization, and Indonesian language stemming, and then feature-extracted using TF-IDF and Count Vectorizer. Evaluation results show that SVM achieved an accuracy of 91.77%, precision of 91.49%, recall of 91.77%, and F1-Score of 91.56%, while RF achieved an accuracy of 90.07%, precision of 91.68%, recall of 90.07%, and F1-Score of 90.55%. ANOVA confirmed that the performance difference between the two algorithms is statistically significant (p-value = 0.0007) with a large effect size (η² = 0.1815). Therefore, SVM is recommended as a more optimal and consistent algorithm for automated sentiment analysis of Indonesian e-commerce reviews, while also providing a replicable methodological framework for similar future research.

Classification is one of the most widely used techniques in machine learning. Text classification is the process of classifying data according to pre-determined groups or classes. Where in most cases, text classification uses labeled training data to obtain the rules used to classify test data into predefined groups. In this study, it is proposed to use CountVectorizer for Indonesian text classification which will be compared with TF-IDF Term Weighting and its three feature levels, namely Character Level, Word Level and N-gram Level as feature extraction which is implemented together with Naive Bayes classification and the BPPPTIndToEngCorpusHalfM dataset. To compare the classification performance, this study uses 10-Fold Cross Validation and Split Data using a ratio of 90:10, while to evaluate the accuracy of the authors using the F1-Score and AUC with the hope that this study will get good accuracy results so that it can be used as a reference to be developed using another method. The F1-Score accuracy obtained in this study was 0.93 and the AUC score was 0.95.