Huda, Denny Setyawan (2024) IMPLEMENTASI ALGORITMA LONG SHORT-TERM MEMORY (LSTM) DALAM KLASIFIKASI JUDUL BERITA. Project Report (Praktek Kerja Lapang dan Magang). Fakultas ilmu komputer UPN "Veteran" Jawa Timur. (Unpublished)
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
cover.pdf Download (494kB) |
|
Text (Bab 1)
bab 1.pdf Download (178kB) |
|
Text (Bab 2)
bab 2.pdf Download (273kB) |
|
Text (Bab 3)
bab 3.pdf Restricted to Repository staff only until 16 September 2028. Download (410kB) |
|
Text (Bab 4)
bab 4.pdf Restricted to Repository staff only until 16 September 2028. Download (1MB) |
|
Text (Bab 5)
bab 5.pdf Restricted to Repository staff only until 16 September 2028. Download (146kB) |
|
Text (Daftar Pustaka)
daftar pustaka.pdf Download (165kB) |
Abstract
The Long Short-Term Memory (LSTM) algorithm is used to classify news titles based on categories. LSTM is a type of artificial neural network designed to remember sequences of data, such as the words in a sentence, which makes it very suitable for Natural Language Processing tasks such as text classification. The implementation process begins by collecting news titles from various relevant online sources. This data then goes through a pre-processing stage that includes cleaning the data from unnecessary characters, tokenization or text splitting, and normalization to transform the words into a uniform form. These steps ensure that the data is in a format that is ready for use by the LSTM model. After pre-processing, the prepared data is used to train the LSTM model. This model is trained to recognize patterns and structures in news headlines so that it can classify them into predetermined categories, such as politics, economics and technology. The implementation results show that the LSTM model is able to classify news headlines with a high level of accuracy, but there are still shortcomings, namely the problem of overfitting. The application of the LSTM algorithm in news headline classification provides significant improvements in classification efficiency and accuracy. This helps in managing news information more effectively, enabling more targeted information dissemination.
| Item Type: | Monograph (Project Report (Praktek Kerja Lapang dan Magang)) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Faculty of Computer Science > Departemen of Informatics |
| Depositing User: | Denny Setyawan Huda |
| Date Deposited: | 16 Sep 2025 08:26 |
| Last Modified: | 16 Sep 2025 08:26 |
| URI: | https://repository.upnjatim.ac.id/id/eprint/43671 |
Actions (login required)
 |
View Item |