BIOSURVEILLANCE UNTUK DETEKSI PENYEBARAN PENYAKIT DI INDONESIA BERDASARKAN TWEETS MENGGUNAKAN ALGORITMA NAÏVE BAYES
| Main Author: | Oktavianto, Lazqar Markus |
|---|---|
| Format: | Thesis NonPeerReviewed Book Image |
| Bahasa: | eng |
| Terbitan: |
, 2018
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/42595/1/Pendahuluan.pdf http://eprints.umm.ac.id/42595/2/BAB%201.pdf http://eprints.umm.ac.id/42595/3/BAB%202.pdf http://eprints.umm.ac.id/42595/4/BAB%203.pdf http://eprints.umm.ac.id/42595/5/BAB%204.pdf http://eprints.umm.ac.id/42595/6/BAB%205.pdf http://eprints.umm.ac.id/42595/7/Poster.jpeg http://eprints.umm.ac.id/42595/ |
Daftar Isi:
- Biosurveillance is the information process, integration, and communication of information that is very likely to relate to humans, animals, or plant health. This study uses a method that can classify what is appropriate with the target class that has been determined. The classification process is based on the extraction of synthetic features. The results of the extraction then use the Naïve Bayes algorithm. The purpose of this study is to tweets data, then it will be visualized in the location map. The Naïve Bayes algorithm was chosen because it has a better level of accuracy than other algorithms. Based on the scenarios that have been done, the accuracy results that result in the tweet data process using the extraction of synthetic features on the test data (test data) of 91.5%. The accuracy results obtained from Named Entity Recognition (NER) to find the location is 96%. The results of testing the system, the average accuracy value is the best. Hopefully the system can be used to develop other supporting features and algorithms.