ANALISIS SENTIMEN ULASAN “OJOL THE GAME” DI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA NAIVE BAYES DAN MODEL EKSTRAKSI FITUR TF-IDF UNTUK MENINGKATKAN KUALITAS GAME

Abstract

Abstrak. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna terhadap game "OJOL THE GAME" di Google Play Store memanfaatakan algoritma Naive Bayes dan model ekstraksi fitur TF-IDF. Data ulasan dikumpulkan melalui teknik web scraping menggunakan Python, kemudian diproses dengan tahapan preprocessing meliputi pembersihan data, case folding, stop word removal, tokenizing, dan stemming. Data yang telah diproses kemudian dianalisis menggunakan algoritma Metode Naive Bayes digunakan untuk mengklasifikasikan sentimen positif dan negatif. Hasil penelitian mengindikasikan bahwa kombinasi antara algoritma Naive Bayes dan TF-IDF memberikan akurasi sebesar94,12%, menunjukkan efektivitas tinggi dalam mengidentifikasi sentimen pengguna. Temuan ini memberikan wawasan berharga  dalam memahami opini pengguna, meningkatkan kualitas game.

Abstract. This study aims to analyze user sentiment towards the game "OJOL THE GAME" on Google Play Store using the Naive Bayes algorithm and the TF-IDF feature extraction model. User review data was collected through web scraping techniques using Python, then processed through preprocessing stages including data cleaning, case folding, stop word removal, tokenizing, and stemming. The processed data was then analyzed using the Naive Bayes algorithm to classify positive and negative sentiments. The results of the study show that the combination of the Naive Bayes algorithm and TF-IDF yielded an accuracy of 94.12%, demonstrating high effectiveness in identifying user sentiment. These findings provide valuable insights into understanding user opinions and improving the quality of the game.