Analisis Sentimen Pelanggan Pempek Cek Ida Terhadap Penilaian Produk Menggunakan Layanan GoFood Pada Aplikasi Gojek Dengan Klasifikasi Support Vector Machine (SVM)

Abstract

This study aims to analyze customer review sentiments towards Pempek Cek Ida products ordered through the GoFood service on the Gojek application by utilizing the Support Vector Machine (SVM) algorithm. This study has two main objectives: classifying customer review sentiments into positive and negative categories, and evaluating the accuracy of the applied classification model. The data used in this study consisted of 135 customer reviews collected manually through data crawling in the period 2020–2022. This research framework uses the SEMMA (Sample Explore, Modify, Model, Access) method. The analysis process begins with a preprocessing step, including cleansing, case folding, tokenizing, filtering, and stemming, to prepare the raw data. The data is then weighted using the Term Frequency-Inverse Document Frequency (TF-IDF) method before being classified using the SVM algorithm. Model evaluation is carried out using a confusion matrix to calculate accuracy, precision, and recall, and validation using K-Fold Cross Validation. The results of the study show that the SVM algorithm has good performance in classifying review sentiments with a high level of accuracy with an accuracy level of 70.88. This research provides strategic benefits for Pempek Cek Ida in understanding customer perceptions, improving product quality, and making service improvements based on customer sentiment data. In addition, this research also contributes to the development of the application of machine learning-based sentiment analysis methods in the culinary sector.