Skripsi

PENGELOMPOKAN ARTIKEL ILMIAH MENGGUNAKAN ROBERTA DAN K-MEANS

---

Penilaian

---

The significant increase in the number of scientific articles published each year presents challenges in managing and utilizing information efficiently. This research aims to develop an automatic scientific article clustering system using a combination of RoBERTa method and K-Means algorithm, as well as evaluate its performance based on the Silhouette Score. The research data consists of 8,675 scientific articles collected through scraping techniques from 12 Sinta-accredited journals (ranks 1-4). The results show variations in clustering performance, with the highest Silhouette Score of 0.8834 for the Obsession Journal: Early Childhood Education Journal and the lowest of 0.5523 for the Journal of Business and Accounting. Data injection testing was conducted to evaluate the relevance between journals, where articles were classified as in-scope or out-scope based on their distance to the cluster centroid.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507001431	T168528	T1685282025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1685282025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer., 2025

Collation

xv, 107 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

518.107

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pengelompokan Data--Roberta dan Algoritma

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment