Analisis Sentimen Ulasan Pengguna Aplikasi Myim3 Pada Situs Google Play Menggunakan Support Vector Machine

Abstract

Technological developments are increasingly rapid, this makes it easier to communicate information and shopping transactions, one of the innovations that are being adopted is digital services, such as self-service. One of the self-services is myim3 which is a product of PT Indosat Ooredoo Hutchison as an internet network service provider company, with the increasing number of users of the application, many opinions or public sentiments are shared in the comments or reviews column, therefore it is necessary to analyze this MyIM3 application review to find out public opinion about the application. The review data is obtained from the Google Play website which is retrieved using the scraping method with the help of 3rd party libraries in python. The amount of data obtained in this study was 3484 data. Experts assist in data labeling to determine positive and negative. In the preprocessing stage, the data is cleaned to reduce the less influential attributes. In the next stage, perform the transformation process with TF-IDF. The classification process is divided into several scenarios with the algorithm used as a support vector machine with 2 kernels, linear and RBF. The best results are in the scenario (70:30) for the linear kernel with 87% accuracy and the scenario (90:10) with 87% accuracy in the RBF kernel. The classification process produces the most frequently occurring words in each sentiment class which is visualized with a word cloud. The word "good" is the most dominant in the positive review data, while the word "network" is the most dominant in the harmful review data of the MyIM3 application

Algoritma Support Vector Machine (Svm) Untuk Analisis Sentimen Ulasan Aplikasi Al Qur’an Digital

“…Tujuan dari preprocessing adalah untuk menghasilkan data yang relevan dengan memperoleh data yang isinya lebih mudah untuk diolah dalam sistem. [9]…”

ANALISIS SENTIMEN DENGAN ALGORITMA NAÏVE BAYES CLASSIFIER TERHADAP ULASAN APLIKASI MY F&B ID

“…Dalam penerapannya, analisis sentimen memiliki dua metode yaitu metode machine learning dan knowledge based method. Machine learning yang digunakan dalam penelitian analisis sentimen yaitu Support Vector Machine [3], Fuzzy Neural Networks [4], Naïve Bayes Classifier [5], Particle Swarm Optimization [6] dan lain-lain. Salah satu jenis knowledge based adalah Lexicon Based [7].…”

Analisis Sentimen Masyarakat terhadap Layanan Provider Internet di Indonesia menggunakan SVM

“…Pada tahap preprocessing, data yang sudah dilabeli oleh pakar akan diolah kembali dengan melakukan tahapan case folding [12], tokenizing [13], filtering [5], dan stemming [14]. Kemudian data yang telah melewati beberapa tahapan tersebut menjadi data bersih ataupun data yang sudah siap untuk diolah menggunakan Teknik SMOTE kemudian dilakukan seleksi fitur Recursive Feature Elimination (RFE) yang kemudian diklasifikasi menggunakan algoritma Support Vector Machine (SVM).…”

“…Selanjutnya pada penelitian [5] algoritma yang digunakan dalam proses klasifikasi adalah Support Vector Machine dengan dua kernel linear dan RBF dan prosesnya dibagi menjadi beberapa skenario. Kernel linier skenario (70:30) dengan akurasi 87%, dan kernel RBF skenario (90:10) dengan akurasi 87% memberikan hasil terbaik.…”