KLASIFIKASI BERBASIS ONTOLOGI UNTUK DOKUMEN TUGAS AKHIR DENGAN METODE PEMBOBOTAN FASTTEXT

IRAWAN, DELLIN and Rodiah, Desty (2024) KLASIFIKASI BERBASIS ONTOLOGI UNTUK DOKUMEN TUGAS AKHIR DENGAN METODE PEMBOBOTAN FASTTEXT. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126080.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021282126080_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282126080_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (518kB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (305kB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (558kB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (149kB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (196kB) | Request a copy
	Text RAMA_55201_09021282126080_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy

Abstract

The classification of undergraduate thesis documents is a crucial process for organizing and categorizing student research into appropriate fields of study. This research develops an ontology-based document classification system for final projects by integrating the FastText word embedding method to improve classification accuracy. The system utilizes BidangIlmuInformatika.owl ontology as a knowledge base to determine the hierarchy and relationships between concepts in the field of informatics. FastText method is implemented to generate word vector representations (word embeddings) capable of capturing semantic context from document text. The classification process is performed by calculating the similarity between document vectors weighted with FastText and concept representations in the ontology. The dataset consists of 160 informatics student undergraduate thesis documents divided into four main areas: Data Science and Pattern Recognition, Distributed Systems, Computer Graphics and Visualization, and Natural Language Processing. Evaluation results show that the proposed system achieves an accuracy of 25%. This is because the concepts within the Data Science and Pattern Recognition domain have a broad knowledge structure that spans nearly all areas of Informatics.

Item Type:	Thesis (Undergraduate)
Subjects:	P Language and Literature > P Philology. Linguistics > P98-98.5 Computational linguistics. Natural language processing Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Dellin Irawan
Date Deposited:	07 Jan 2025 08:39
Last Modified:	07 Jan 2025 08:39
URI:	http://repository.unsri.ac.id/id/eprint/162934

Actions (login required)

View Item