Pembobotan TF-IDF Menggunakan Naïve Bayes pada Sentimen Masyarakat Mengenai Isu Kenaikan BIPIH

Abstract

The Ministry of Religious Affairs proposes to increase the cost of Hajj Travel (Bipih) in 1444 H/2023 M to Rp.69.19 million. There is a fairly high increase in costs compared to 2022. This raises sentiment in the community, there are public opinions for and against the issue of rising Bipih on social media twitter. The purpose of this study was to analyze the sentiment on the issue of increasing the cost of Hajj Travel and to prove whether Naive Bayes is a good classifier of text on the issue of incremental sentiment. Naive Baye is one of the best text classifier algorithms. Data taken from social media twitter. The Data are grouped into pro and Contra opinions and then processed using python programming language and jupyter as text editor. Data used as much as 850 data. The Data is divided into training data and testing data with a ratio of 80:20. With the number of training data of 679 data and the number of testing data of 170 data. Then implement Multinominal Naive Bayes algorithm (MNB) as text classifier and word weighting using TF-IDF. The test results obtained accuracy value of 89% and ROC value of 0.91. It is proven that Multinominal Naive Bayes algorithm (MNB) is a good classifier of text for sentiment analysis of opinion on the issue of increasing the cost of Hajj travel because it is included in the Excellent Classification.