ANALISIS SENTIMEN TERHADAP CYBERBULLYING PADA APLIKASI X MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

AZZAHRA, VALYSSA and Rodiah, Desty (2024) ANALISIS SENTIMEN TERHADAP CYBERBULLYING PADA APLIKASI X MENGGUNAKAN METODE LONG SHORT-TERM MEMORY. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126089.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_55201_09021282126089_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126089_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy

Abstract

The rapid advancement of the internet and information technology has transformed many aspects of life, including communication through social media. Application X, previously known as Twitter, has become a primary platform for sharing information. However, this convenience also presents challenges, such as cyberbullying, a harmful behavior including threats that affect users' mental health. This study analyzes sentiments related to cyberbullying on Application X using Long Short-Term Memory (LSTM) combined with Word2Vec. The addition of the Word2Vec feature aims to address LSTM's limitations in understanding syntactic structures and word relationships, thereby enhancing the model's ability to capture context and language nuances. The dataset consists of 1520 tweets, with 761 positive sentiments and 759 negative sentiments. Hyperparameter tuning was conducted using a grid search with a total of 216 experiments, resulting in the best configuration at experiment 183 with 512 hidden units, a dropout rate of 0.3, recurrent dropout of 0.2, batch size of 64, and 10 epochs, achieving the highest accuracy of 91.77%. This study demonstrates the effectiveness of combining LSTM and Word2Vec in identifying sentiments related to cyberbullying on Application X.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	analisis sentimen, cyberbullying, Long Short-Term Memory (LSTM), Word2Vec, Aplikasi X
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Valyssa Azzahra
Date Deposited:	07 Jan 2025 02:00
Last Modified:	07 Jan 2025 02:00
URI:	http://repository.unsri.ac.id/id/eprint/162743

Actions (login required)

View Item