Text

EXTRACTIVE SUMMARIZATION BERITA BERBAHASA INDONESIA MENGGUNAKAN LSTM

---

In the internet era, the vast amount of available information makes it challenging for readers to find relevant news and requires time to read entire documents to extract desired information. Therefore, summaries are needed to help readers extract and represent the most crucial information from news articles efficiently and effectively. This research focuses on developing an Extractive Summarization model for Indonesian news texts using Long Short-Term Memory (LSTM) networks due to their ability to maintain memory of word relationships. The designed model achieved a ROUGE-1 Precision of 0.3287, Recall of 0.6045, and F1-score of 0.4207 as well as a ROUGE-2 Precision of 0.2159, Recall of 0.4351, and F1-score of 0.2841, with a Loss of 0.09 and Validation Loss of 0.0898. The dataset comprised 18,952 data points, with 14,469 for training, 2,241 for validation, and 2,242 for testing

---

Availability

Detail Information

Series Title

-

Call Number

T1563432024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xii, VI-1 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Kecerdasan Buatan
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEW

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment