Skripsi

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

---

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.

---

Availability

Detail Information

Series Title

-

Call Number

T1627432024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xxv, 120 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Teknik Informatika
Program Aplikasi dengan Kegunaan Khusus

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment