Claim Missing Document
Check
Articles

Found 1 Documents
Search

Comparison of the Naïve Bayes Method and Support Vector Machine in Sentiment Analysis of Genshin Impact Game Reviews Pratama, Mr. Aldiansyah; Hasan, Fuad Nur
International Journal of Mechanical Computational and Manufacturing Research Vol. 13 No. 2 (2024): August: Mechanical Computational And Manufacturing Research
Publisher : Trigin Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/computational.v13i2.198

Abstract

Genshin Impact was a successful and quite popular game during the 4 years of its release, but behind this there are several positive or negative opinions about this game, both internal and external. Sentiment Analysis is a technique that can identify an opinion in a text that is managed, be it a comment or review. The aim of the research is to compare two algorithms, namely Support Vector Machine and Naïve Bayes, in classifying Genshin Impact game reviews on Google Playstore. This method has several stages, namely crawling data, text preprocessing, using a confusion matrix and k-fold cross validation, all of these stages are carried out using libraries in Python with 1198 review data divided between test data and training data by 90:10 which produces a support vector machine of 73% accuracy, 75% precision, 64% recall and f1-score of 64% while naïve bayes is 72% accuracy, 68% precision, 68% recall and f1-score of 68%. With this comparison it is concluded that support vector machine has a higher evaluation value than naïve bayes, while it is known that the majority of review data has a negative value regarding Genshin Impact game reviews.