<![CDATA[Sentiment analysis is the process of automatically extracting, understanding and processing unstructured text data to obtain sentiment information contained in opinions or opinion statements that are positive, negative, or neutral. The data is classified using Naive Bayes. The analysis is divided into 10 stages: crawling, labeling, data cleaning, pre-processing, case folding, stopwords removal, tokenizing, stemming, word weighting, and sentiment classification. Word weighting employs the TF-IDF method (Term Frequency - Inverse Document Frequency). The data is classified into 3 classes: positive, negative, and neutral. Subsequently, the data is evaluated using confusion matrix testing with parameters such as precision, recall, f1-score, and support. The test results indicate that for the 3-class test (positive, negative, and neutral), the best result was achieved with an accuracy of 71.33%.]]>
Copyrights © 2023
