Sentiment Analysis and Classification of Forest Fires in Indonesia

Abstract

so the preprocessing process must be carried out as was done in research [5], which retrieved Twitter data on the theme of COVID 2019. Moreover, weighting must be applied to tasks that must be completed prior to classification. This study uses VADER or commonly known as the lexicon. [6] It uses a lexicon that combines lexical dictionary features as a polarity assessment. Sentiment scores of 5 additional criteria, namely exclamation marks, large alphabet, level of word order, polarity shift due to the term "but," and using the tri-gram feature to study negation [7]. Once the text has been labeled, we will classify it using the sentiment analysis. The Nave Bayes technique, Random Forest, and SVM are some reliable classifications that have been demonstrated in numerous research (Support Vector Machine). A popular algorithm that is frequently employed by researchers is Naïve Bayes. The following researchers have used the Naive Bayes method for sentiment analysis research: : [8] analyzing the online store JD.ID, [9] regarding awareness of procedures to prevent COVID 2019. Random Forest is rarely implemented in research on sentiment analysis, although it has recently been investigated to gauge its accuracy. It is used by a number of researchers, including [10], who achieves an accuracy of about 0.829. Moreover, the SVM (Support Vector Machine) approach, whose accuracy is 85%, is also being investigated in sentiment analysis study by [11]. Hence, researchers want to compare the values of the 3 methods namely Naïve Bayes, Random Forest and SVM (Support Vector Machine) to find out the difference in accuracy of the three when using the same data. As for the accuracy will be calculated using the calculation on the confusion matrix. In addition, the researcher also wants to compare the results of classifying sentiment statements which are divided into positive, negative and neutral sentiments.