Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Performance of Machine Learning Algorithms on Automatic Summarization of Indonesian Language Texts

Jurnal Online Informatika · Vol. 10 No. 1 (2025) · hlm. 196–204

DOI
10.15575/join.v10i1.1506
ISSN
2527-9165, 2528-1682
Terbit
2025-05-13
Penerbit
Sunan Gunung Djati State Islamic University Bandung
Bahasa
en
Lisensi
creativecommons.org/licenses/by-nd/4.0/

Abstrak

Automatic text summarization (ATS) has become an essential task for processing huge amounts of information efficiently. ATS has been extensively studied in resource-rich languages like English, but research on summarization for under-resourced languages, such as Bahasa Indonesia, is still limited. Indonesian presents unique linguistic challenges, including its agglutinative structure, borrowed vocabulary, and limited availability of high-quality training data. This study conducts a comparative evaluation of extractive, abstractive, and hybrid models for Indonesian text summarization, utilizing the IndoSum dataset which contains 20,000 text-summary pairs. We tested several models including LSA (Latent Semantic Analysis), LexRank, T5, and BART, to assess their effectiveness in generating summaries. The results show that the LexRank+BERT hybrid model outperforms traditional extractive methods, achieving better ROUGE precision, recall, and F-measure scores. Among the abstractive methods, the T5-Large model demonstrated the best performance, producing more coherent and semantically rich summaries compared to other models. These findings suggest that hybrid and abstractive approaches are better suited for Indonesian text summarization, especially when leveraging large-scale pre-trained language models.

Kata kunci

Jaringan kolaborasi para penulis

8 penulis · 12 tautan kepenulisan bersama · 4 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Muhammadiyah University of Surakarta
  • Institut Teknologi Sepuluh Nopember
  • Universitas Muhammadiyah Madiun
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Siti RochimahInstitut Teknologi Sepuluh Nopember1
Fernandes SinagaInstitut Teknologi Sepuluh Nopember1
Mohammad Faqih Eza 'AmmarMuhammadiyah University of Surakarta1
Diah PriyawatiMuhammadiyah University of Surakarta1
Fatah Yasin Al IsyadiMuhammadiyah University of Surakarta1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210216628, pertama di-harvest 21 Nov 2026, terakhir terlihat 21 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Performance of Machine Learning Algorithms on Automatic Summarization of Indonesian Language Texts</dc:title><dc:creator>Galih Wiratmoko</dc:creator><dc:creator>Husni Thamrin</dc:creator><dc:creator>Endang Wahyu Pamungkas</dc:creator><dc:subject>text summarization</dc:subject><dc:subject>Indonesian language</dc:subject><dc:subject>extractive summarization</dc:subject><dc:subject>abstractive summarization</dc:subject><dc:subject>hybrid summarization</dc:subject><dc:subject>LexRank</dc:subject><dc:subject>BERT</dc:subject><dc:subject>T5</dc:subject><dc:subject>BART</dc:subject><dc:subject>latent semantic analysis</dc:subject><dc:subject>low-resource languages</dc:subject><dc:subject>ROUGE evaluation</dc:subject><dc:description xml:lang="en">Automatic text summarization (ATS) has become an essential task for processing huge amounts of information efficiently. ATS has been extensively studied in resource-rich languages like English, but research on summarization for under-resourced languages, such as Bahasa Indonesia, is still limited. Indonesian presents unique linguistic challenges, including its agglutinative structure, borrowed vocabulary, and limited availability of high-quality training data. This study conducts a comparative evaluation of extractive, abstractive, and hybrid models for Indonesian text summarization, utilizing the IndoSum dataset which contains 20,000 text-summary pairs. We tested several models including LSA (Latent Semantic Analysis), LexRank, T5, and BART, to assess their effectiveness in generating summaries. The results show that the LexRank+BERT hybrid model outperforms traditional extractive methods, achieving better ROUGE precision, recall, and F-measure scores. Among the abstractive methods, the T5-Large model demonstrated the best performance, producing more coherent and semantically rich summaries compared to other models. These findings suggest that hybrid and abstractive approaches are better suited for Indonesian text summarization, especially when leveraging large-scale pre-trained language models.</dc:description><dc:publisher>Sunan Gunung Djati State Islamic University Bandung</dc:publisher><dc:date>2025-05-13</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.15575/join.v10i1.1506</dc:identifier><dc:identifier>10.15575/join.v10i1.1506</dc:identifier><dc:source>Jurnal Online Informatika; Vol 10 No 1 (2025); 196-204</dc:source><dc:source>2527-9165</dc:source><dc:source>2528-1682</dc:source><dc:language>en</dc:language><dc:relation>https://join.if.uinsgd.ac.id/index.php/join/article/download/1506/355</dc:relation><dc:rights>https://creativecommons.org/licenses/by-nd/4.0/</dc:rights></oai_dc:dc>