KLASIFIKASI BERITA MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM)

ELWINA, ELWINA and Yusliani, Novi and Satria, Hadipurnawan (2024) KLASIFIKASI BERITA MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021182025018.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182025018_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (713kB)
	Text RAMA_55201_09021182025018_0008118205_0018048003_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (177kB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (197kB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (355kB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (290kB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (79kB) | Request a copy
	Text RAMA_55201_09021182025018_0008118205_0018048003_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7kB) | Request a copy

Abstract

In today's digital information age, the abundance of news available on the internet creates the need for an automated system that can classify news very accurately based on its category. This research presents an approach that uses Long Short-Term Memory (LSTM) to classify news and Term Frequency-Inverse Document Frequency (TF-IDF) as word weighting. The LSTM method is used to process news text and extract features that represent relevant news content. The data used is multiclass and taken from Kaggle with a total data of 32,259 news titles which are then divided into 70% training data and 30% test data. After testing the test data, the LSTM classification performance results are obtained with an accuracy value of 87%, precision 88%, recall 87%, and f-score 88%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi, Long Short-Term Memory, Term Frequency-Inverse Document Frequency, multiclass.
Subjects:	T Technology > T Technology (General) > T57-57.97 Applied mathematics. Quantitative methods > T57.5 Data processing Cf. HF5548.125+ Business data processing Operations research. Systems analysis
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Elwina Elwina
Date Deposited:	30 Jan 2024 07:41
Last Modified:	30 Jan 2024 07:41
URI:	http://repository.unsri.ac.id/id/eprint/140149

Actions (login required)

View Item