Skripsi

KOMBINASI ARSITEKTUR TRANSFORMER DAN GATED RECURRENT UNIT (GRU) DALAM ANALISIS SENTIMEN TERHADAP ULASAN LAYANAN TELEMEDICINE

---

Telemedicine services are healthcare services and the exchange of medical information conducted remotely through Information and Communication Technology. Service providers need to adapt to ongoing developments in order to meet user needs and expectations. One of the efforts to support this development is by analyzing user satisfaction or perceptions using sentiment analysis methods. This study proposes a combination of the Transformer architecture and Gated Recurrent Unit (GRU) for sentiment analysis of the Alodokter and Klikdokter applications. The Transformer is placed in the first block to capture global information through the self-attention mechanism. The GRU is placed in the second block to preserve sequential information that may be lost when processed by the Transformer architecture. Model performance is evaluated by measuring the average performance using accuracy, precision, recall, and F1-score. The evaluation results for the Alodokter application show an accuracy of 97.22%, precision of 97.24%, recall of 97.23%, and an F1-score of 97.22%. Meanwhile, the Klikdokter application achieves an accuracy of 96.31%, precision of 96.30%, recall of 96.40%, and an F1-score of 96.33%. An accuracy value above 95% indicates that the model is able to correctly classify sentiment labels in telemedicine service reviews across the entire test dataset. A precision value above 95% indicates that most sentiment predictions generated by the model are accurate. A recall value above 95% indicates that the model successfully recognizes most of the data according to their sentiment labels. An F1-score above 95% indicates a balance between precision and recall, demonstrating that the model has stable performance in analyzing the sentiment of telemedicine service reviews.This study shows that the combination of the Transformer and GRU models can improve the performance of sentiment analysis for telemedicine service reviews.

---

Availability

Detail Information

Series Title

-

Call Number

T1944182026

Publisher

Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2026

Collation

xvi, 50 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Kecerdasan Buatan
Prodi Ilmu Matematika

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment