Klasifikasi Opini Terhadap Pertanian Sawit (Palm Oil) Indonesia Menggunakan Naïve Bayes

Hafiz Irsyad, Hafiz Irsyad and M Rizky Pribady, M Rizky Pribady (2020) Klasifikasi Opini Terhadap Pertanian Sawit (Palm Oil) Indonesia Menggunakan Naïve Bayes. JATISI (Jurnal Teknik Informatika dan Sistem Informasi), 6 (2). pp. 230-239. ISSN ISSN 2407, E-ISSN 2503-2933

Text Klasifikasi Opini Terhadap Pertanian Sawit (Palm Oil) Indonesia Menggunakan Naïve Bayes.pdf - Other Download (203kB)

Abstract

Last three years the production of oil palm agriculture has been considered to have increased significantly. Indonesia is the largest contributor to palm oil with Malaysia, which is 85-90% of the total world palm oil yield. With so much information on Indonesian oil palm on Twitter so that it can be used to see public opinion about Indonesian oil palm. In this study managed to collect tweet data from 28 August 2019 to 21 June 2018 resulting in 1015 tweets. In order to see the tweets, the categories are categorized into positive, negative and neutral, then the tweets are classified using the naïve Bayes method and using the Orange tools. Meanwhile, to do data crawling using Twitter API facilities. Of the 1015 data tweets 70% is used for training data and 30% for testing data. In the application of calisification with the naïve bayes method it produces an average accuracy of 0.83337% for the average of all categories, for precision obtains 0.80303% for the average of all categories, and for recall produces 0.90853% for all average categories. With this level of accuracy the Naïve Bayes method works in line with expectations.

Item Type:	Article
Uncontrolled Keywords:	Naïve Bayes, Indonesian Palm Oil, Opinion, Classification, Naive Bayes, Sawit Indonesia, Opini, Klasifikasi
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User:	Mrs Ni Made Yunia Dwi Savitri
Date Deposited:	17 Nov 2022 01:34
Last Modified:	17 Nov 2022 01:34
URI:	http://eprints.triatmamulya.ac.id/id/eprint/1776

Actions (login required)

View Item