ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI IPUSNAS DI GOOGLE PLAYSTORE DENGAN METODE BI-LSTM DAN FASTTEXT

NURHALIZA, LIDIA and Rodiah, Desty (2025) ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI IPUSNAS DI GOOGLE PLAYSTORE DENGAN METODE BI-LSTM DAN FASTTEXT. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_55201_09021182126008_cover.jpeg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (399kB) | Preview
	Text RAMA_55201_09021182126008.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021182126008_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021182126008_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (376kB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (209kB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (164kB) | Request a copy
	Text RAMA_55201_09021182126008_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

Digital libraries, such as iPusnas, have become essential solutions for improving access to reading materials in the digital era. User reviews of the iPusnas application on the Google Play Store contain valuable information that can be utilized to enhance services and guide application development. This study aims to develop a sentiment analysis system for user reviews of the iPusnas application by employing a combination of Bidirectional Long Short-Term Memory (Bi-LSTM) and FastText methods, and to evaluate its performance based on accuracy, precision, recall, and F1-score metrics. Bi-LSTM is an extension of LSTM that processes data in both forward and backward directions, enabling more effective contextual understanding of sentences. Meanwhile, FastText is a word representation technique that incorporates subword information, allowing it to generate more informative word vectors, particularly for languages with complex morphology. The dataset consists of 10,149 reviews classified into three sentiment categories: positive, neutral, and negatif. Optimal results were obtained using a configuration of 64 LSTM Units, 0.2 LSTM dropout, 32 dense Units, a learning rate of 0.001, batch size of 16, and 15 epochs, achieving an accuracy of 79%. The model performed well in classifying positive (F1-score 84%) and negatif (F1-score 83%) sentiments, but showed suboptimal performance in identifying neutral sentiment (F1-score 55%). The developed system can assist iPusnas application developers in better understanding user opinions to improve the quality of digital library services.opinions more effectively to improve the quality of digital library services.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Analisis Sentimen, Bi-LSTM, FastText, iPusnas, Perpustakaan Digital
Subjects:	P Language and Literature > P Philology. Linguistics > P98-98.5 Computational linguistics. Natural language processing T Technology > T Technology (General) > T57.6-57.97 Operations research. Systems analysis > T57.97 Search theory T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.5 General works Management information systems Cf. HD30.213 Industrial management Cf. HF5549.5.C6+ Communication in personnel management Cf. TS158.6 Automatic data collection systems (Production control)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Lidia Nurhaliza
Date Deposited:	15 May 2025 04:45
Last Modified:	15 May 2025 04:45
URI:	http://repository.unsri.ac.id/id/eprint/172525

Actions (login required)

View Item