Gunawan, Anita Caroline and Elfitriani, Erin and Khotimah, Purnomo Husnul and Kurniasari, Dian (2026) Multi-Class Named Entity Recognition for Health Information Extraction Using Indonesian Online News Headlines. In: 2025 International Conference on Computer, Control, Informatics and its Applications (IC3INA), 15-16 October 2025, Jakarta, Indonesia.

Text Multi-Class_Named_Entity_Recognition_for_Health_Information_Extraction_Using_Indonesian_Online_News_Headlines.pdf Download (3MB)

Abstract

The increasing intensity of digital information flow has driven the demand for technologies capable of Automatically interpreting and extracting data from unstructured sources, particularly in the healthcare domain. In the context of infectious disease outbreaks, such as COVID-19, early information often emerges through online media but is conveyed in diverse and non-standardized forms, making it difficult to process without auto mated systems. This study develops an Indonesian Named Entity Recognition (NER) system focused on online news headlines concerning infectious diseases, adopting a multi-entity approach that includes Person (PER), Organization (ORG), Location (LOC), and Disease (DIS). Three model architectures were employed, namely BiLSTM, BiLSTM-CRF, and IndoBERT, supported by FastText embeddings and Part-of-Speech (POS) tagging features. The evaluation results indicate that IndoBERT achieved the best overall performance, particularly in recognizing disease entities, with the highest F1-score of 79.64%. This system has strong potential for application in the automated monitoring and early detection of infectious disease outbreaks in Indonesia.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > QA Mathematics
Divisions:	Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Matematika
Depositing User:	DIAN KURNIASARI
Date Deposited:	17 Apr 2026 02:42
Last Modified:	17 Apr 2026 02:42
URI:	http://repository.lppm.unila.ac.id/id/eprint/54838

Actions (login required)

View Item