The Detection of Indonesian Hoax Content about COVID-19 Vaccine using Naive Bayes Multinomial Method
One media currently famously used in all worlds is twitter. The ease of dissemination and the exchange of information is accelerating. Every day, millions of tweets exist using various information, such as politics, technology, sports, academics, and others. The information that is widely found is about COVID-19-19 nowadays. The information on Twitter is not entirely accurate or according to facts and needs to be proven true. Therefore, this study aims to try to detect the information contained in Indonesia using methods of Naive Bayes Multinomial by using the Information Gain feature selection. The classification process is carried out by crawling tweets, preprocessing, then using feature selection, namely Information Gain, and classification using the Multinomial Naive Bayes method. Meanwhile, the validation needs in this study use k-fold cross-validation where the existing dataset is divided into training and testing data that will be tested with a confusion matrix. Researchers have carried out the confusion matrix testing process using 720 datasets divided as train data & the test data received an average accuracy value of 81.39%, precision of 80.36%, and recall of 79.73%. The highest accuracy is using k-fold two. The accuracy value reaches 88.8%, the precision value is 79.1%, and the recall value is 86.3%. The lowest accuracy was obtained on the 8th k-fold with an accuracy value of 73.6%, precision 75.4%, and recall 86.9%.
Copyright (c) 2023 ANNISA PUSPA KIRANA, Gunawan Budi Prasetyo, Ela Widya Lestari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).