Skripsi

SISTEM KOREKSI EJAAN BAHASA INDONESIA PADA BERITA ONLINE MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

---

Penilaian

---

When writing news articles, ease of understanding and comprehension by readers is something that must be considered by the writer. One of the crucial things in writing a work is spelling errors or what are called typos. To avoid misinterpretation by readers, an automatic spelling correction system is needed in order to detect and correct spelling errors. One of the approaches used is the Long Short-Term Memory method using word2vec or TF-IDF to produce the probability of each unique word from the training data. In the experiment, the highest accuracy value was obtained at 0.3273 using the word2vec configuration. The test results show a Root Mean Square Error value of 0.997 with the distance between the probability of the predicted results and the ground truth ranging from 0.913 to 0.999.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407005259	T155196	T1551962024	Central Library (References)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1551962024

Publisher

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

Collation

xiv, 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