Optimalisasi Peringkasan Artikel Teks Bahasa Indonesia dengan Kombinasi TextRank dan Graph Neural Network Sederhana

Syatria, Muhammad Rifqi
Mulyana, Dadang Iskandar

Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi)
Vol 10 No 1 (2026): JANUARY 2026

The delivery of digital information in Indonesian-language news presents challenges in efficiently capturing the core information. This study proposes a combination of the TextRank algorithm and a simple Graph Neural Network (GNN) to improve the quality of automatic text summarization. TextRank is used to construct a sentence graph based on TF-IDF similarity and cosine similarity, followed by training a SimpleGNN model to optimize sentence scores. Evaluations were conducted on 1,000 articles from the Liputan6 dataset using the ROUGE metric (ROUGE-1, ROUGE-2, and ROUGE-L). The results show that this combined method improves performance compared to pure TextRank, especially in capturing semantic relationships between sentences. This study demonstrates that the integration of a simple GNN can enrich representations in graphs and provide more informative and contextual summaries.