ANALISIS SENTIMEN PERSEPSI PENGGUNA TWITTER MENGENAI PENERAPAN PENDETEKSI WAJAH DENGAN PENDEKATAN LONG SHORT TERM MEMORY (LSTM)

GUSNAINI, RIZKA and Utami, Alvi Syahrini and Kurniati, Junia (2024) ANALISIS SENTIMEN PERSEPSI PENGGUNA TWITTER MENGENAI PENERAPAN PENDETEKSI WAJAH DENGAN PENDEKATAN LONG SHORT TERM MEMORY (LSTM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025079.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282025079_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282025079_0022127804_0026068907_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (712kB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (199kB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (134kB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (138kB) | Request a copy
	Text RAMA_55201_09021282025079_0022127804_0026068907_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (506kB) | Request a copy

Abstract

In this study, an analysis of Twitter users' opinions and perceptions regarding the implementation of facial recognition will be conducted, with a focus on performance and privacy security. The method to be applied is Long Short Term Memory (LSTM) and Word2Vec weighting. LSTM, also known as deep learning, is chosen because it can process and retain long-term information, making it suitable for analyzing complex and contextual texts such as Twitter posts. The results of experimental testing show a good level of accuracy, with values of accuracy 0.7739, precision 0.7738, recall 0.7739, and F1-Score 0.7737. The use of hyperparameters such as dropout 0.3, hidden unit 64, recurrent dropout on LSTM layer 0.8, Epochs 30, and batch size 128 contribute positively to the model's performance. This research provides an in-depth understanding of users' attitudes towards facial recognition technology, especially in the context of performance and privacy security, and offers insights into the development of more responsive and high-quality technology.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Analisis Sentimen, Confusion Matrix, Long Short Term Memory, Word Embedding, Word2Vec
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Rizka Gusnaini
Date Deposited:	09 Jul 2024 02:57
Last Modified:	09 Jul 2024 02:57
URI:	http://repository.unsri.ac.id/id/eprint/149929

Actions (login required)

View Item