PENERAPAN METODE LONG-SHORT TERM MEMORY (LSTM) DALAM ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN APLIKASI GOJEK MELALUI PLAY STORE

YESIKAL, NABILLA and Yusliani, Novi and Rachmatullah, Muhammad Naufal (2025) PENERAPAN METODE LONG-SHORT TERM MEMORY (LSTM) DALAM ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN APLIKASI GOJEK MELALUI PLAY STORE. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021382126159_COVER.PNG]
Preview
Image
RAMA_55201_09021382126159_COVER.PNG - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_55201_09021382126159.pdf] Text
RAMA_55201_09021382126159.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_TURNITIN.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (11MB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_01_front_ref.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_01_front_ref.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_02.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (492kB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_03.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (555kB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_04.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_04.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (2MB)
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_05.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_06.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (196kB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_07_ref.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_07_ref.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (277kB) | Request a copy
[thumbnail of RAMA_55201_09021382126159_0008118205_0001129204_08_lamp.pdf] Text
RAMA_55201_09021382126159_0008118205_0001129204_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (132kB) | Request a copy

Abstract

This study discusses the application of the Long Short-Term Memory (LSTM) method in aspect-based sentiment analysis of reviews on the Gojek application in the Google Play Store. By utilizing Word2Vec for word representation and Latent Dirichlet Allocation (LDA) for topic modeling, this research aims to identify and classify user sentiment regarding various features of the Gojek app, such as user experience, service, pricing, and privacy & safety. The dataset consists of Indonesian-language reviews that have undergone preprocessing steps such as case folding, cleaning, normalization, tokenization, stopword removal, and stemming. Topic modeling is performed to determine the main aspects in the reviews, which are then used for sentiment analysis with the LSTM model. The experiment is conducted using the best hyperparameter configuration, including 128 LSTM units, dropout 0.2, recurrent dropout 0.3, learning rate 0.001, batch size 128, and 10 epochs.The evaluation results show that the LSTM model performs well, achieving 91% accuracy, 97% precision, 91% recall, and 94% F1-score. This approach is expected to contribute to improving the quality of Gojek's services

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Analisis Sentimen, Gojek, LSTM, Word2Vec, Word Embedding, LDA, Confusion Matrix
Subjects: T Technology > T Technology (General) > T1-995 Technology (General)
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Nabilla Yesikal
Date Deposited: 20 Mar 2025 05:15
Last Modified: 20 Mar 2025 05:15
URI: http://repository.unsri.ac.id/id/eprint/169465

Actions (login required)

View Item View Item