Mardiyani, Khairunnisa' Rahma (2020) Identifikasi Keyword pada Konten Publikasi Jurnal Ilmiah untuk Studi Kasus Pencarian Publikasi Online ITS (POMITS). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
05111640000187-Undergraduate_Thesis.pdf Download (3MB) | Preview |
Abstract
Di era modern ini, kebutuhan dalam bidang ilmiah semakin meningkat, jumlah publikasi ilmiah semakin lama semakin banyak. Tujuan dari sistem yang dibuat pada penelitian ini adalah mangatasi keterbatasan pencarian Publikasi Online ITS (POMITS) di Departemen Teknik Informatika ITS sehingga nantinya pengguna dapat melakuakan pencarian berdasarkan software, metode, dan keyword. Masalah ini dapat diatasi dengan menggunakan Named Entity Recognition (NER). Namun dikarenakan model NER Bahasa Indonesia milik SpaCy belum tersedia maka dalam penelitian ini juga dibangun model NER Bahasa Indonesia baru dengan Prodigy sebagai alat bantu anotasinya. Dalam tugas akhir ini, ekstraksi setiap anotasi pada konten POMITS menjadi sebuah metadata dilakukan dengan mendeteksi named entity berupa software, metode, dan keyword menggunakan model Named Entity Recognition (NER). Hasil anotasi NER yang merupakan metadata POMITS disimpan dalam bentuk pasangan triplets pada triple store Apache Jena Fuseki yang selanjutnya dapat digunakan untuk menjawab query tentang software, metode, dan keyword.
======================================================================================================================
Nowadays, the needs in the scientific field and the number of scientific publications are increasing. The system's purpose in this study is to overcome the limitations of ITS Online Publication (POMITS) search in the Informatics Department. Later, users can carry out searches based on software, methods, and keywords. This problem can be overcome by using Named Entity Recognition (NER). However, because SpaCy's Indonesian NER model is unavailable at this time, this study also developed a new Indonesian NER model with Prodigy as an annotation tool. In this study, Named Entity Recognition was used to identify named entities that explain software, methods, and keywords. Those keywords later used as annotations of POMITS articles. The annotations are stored in the form of triplets pairs in the Apache Jena Fuseki triple store, which can then be used to answer queries about software, methods, and keywords.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Named Entity Recognition (NER), Anotasi, Prodigy, Apache Jena Fuseki, Annotation |
| Subjects: | Q Science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Faculty of Information and Communication Technology > Informatics > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Khairunnisa Rahma Mardiyani |
| Date Deposited: | 04 Aug 2020 08:49 |
| Last Modified: | 11 May 2023 01:51 |
| URI: | http://repository.its.ac.id/id/eprint/76536 |
Actions (login required)
 |
View Item |