Skripsi

ANALISIS SENTIMEN TERHADAP CONTENT CREATOR PAPI ABE MENGGUNAKAN METODE LONG SHORT TERM MEMORY

---

The phenomenon of Papi Abe as a family content creator who has gone viral on TikTok has generated a wide range of public responses, both positive and negative, particularly regarding father-child interactions in parenting content and the potential for child exploitation. Therefore, it is important to understand public opinions toward Papi Abe as a basis for evaluating and improving content quality, which motivates the use of sentiment analysis. This study employs the Long Short-Term Memory (LSTM) method due to its capability to understand context and sequential patterns in social media text data. The dataset consists of 10,659 Indonesian-language comments collected from TikTok and X platforms on Papi Abe's account. The experimental results indicate that the best-performing model was obtained using LSTM parameters with 128 units, a dropout rate of 0.5, and a recurrent dropout of 0.5. The optimizer used was Adam with a learning rate of 1e-4, trained for 50 epochs with a batch size of 64. The model achieved a performance of 0.9071 accuracy, 0.9069 precision, 0.9070 recall, and an F1-score of 0.9069. These results demonstrate that the LSTM method is effective in sentiment in the analysis of the Papi Abe phenomenon. Keywords: Sentiment Analysis, Long Short-Term Memory (LSTM), Social Media Comments, Papi abe

---

Availability

Detail Information

Series Title

-

Call Number

T1955152026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvi, V-23 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Pencipta Konten

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment