ANALISIS SENTIMEN TWEET PIALA DUNIA U-20 MENGGUNAKAN METODE LONG SHORT TERM MEMORY

HANIVANSYAH, RADIVAN RAHMATIKA and Yusliani, Novi and Rachmatullah, Muhammad Naufal (2023) ANALISIS SENTIMEN TWEET PIALA DUNIA U-20 MENGGUNAKAN METODE LONG SHORT TERM MEMORY. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021381924132.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381924132_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_09021381924132_0008118205_0001129204_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (894kB)
	Text RAMA_55201_09021381924132_0008118205_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (381kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (219kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (527kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (287kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (34kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (112kB) | Request a copy
	Text RAMA_55201_09021381924132_0008118205_0001129204_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (169kB) | Request a copy

Abstract

Sentiment analysis is the process of analyzing opinions, sentiments, and so on. The purpose of sentiment analysis is to collect polarity in sentences. What is analyzed are reviews/opinions that are often found on social media, blogs, and many more. One of the most frequently used social media is Twitter. Twitter has many features such as being able to create tweets. Tweets made by users are usually in the form of opinions, or comments that are positive, neutral, or negative. In this study, sentiment analysis was carried out on twitter. The dataset used is a collection of tweets that have positive and negative sentiment labels. The method used is Long short-term memory (LSTM). The testing data format in this research uses confusion matrix in the form of accuracy, precision, recall, and F-1 Score. The results of this study show that the LSTM configuration with a dropout of 0.5 and a learning rate of 0.0001 produces good training and testing results with an Accuracy value of 82.6%, Precision value of 85.7%, Recall value of 80.1%, and F-1 Score value of 82.8%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Analisis Sentimen, Twitter, LSTM
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Radivan Rahmatika Hanivansyah
Date Deposited:	23 Nov 2023 05:51
Last Modified:	23 Nov 2023 05:51
URI:	http://repository.unsri.ac.id/id/eprint/130926

Actions (login required)

View Item