<![CDATA[The increasing number of gamers has increased the demand for Graphics Processing Unit (GPU) products, one example of which is the Nvidia RTX product. Many users submit their reviews on social media Twitter in the form of tweets. These Tweets can be analyzed to determine the quality of a product. But most of the tweets talking about the product as a whole ignoring the category aspects of the product, making it difficult for both users and companies to pinpoint which aspects need attention. In this research, a multi-aspect based sentiment analysis will be carried out on tweets on Nvidia RTX products based on aspects of the product. The classification method used is Naive Bayes Classifier which will then compare feature extraction using Word2Vec and GloVe. Performance parameters are measured using a confusion matrix to produce values for accuracy, precision, recall, and f1-score. The highest accuracy results obtained were 60.71% on the price aspect, GloVe feature extraction, and classification with Gaussian Naive Bayes.Keywords: naive bayes classifier; Word2Vec; GloVe; confusion matrix; multi-aspect sentiment analysis]]>
Copyrights © 2023
