Skripsi

ANALISIS SENTIMEN CUSTOMER REVIEW DI E-COMMERCE TOKOPEDIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM) DAN ADAPTIVE SYNTHETIC SAMPLING (ADASYN)

---

Penilaian

---

Sentiment analysis is the process of automatically understanding, extracting, and processing textual data to uncover information about opinions contained within the data, determining whether they are negative or positive. This study aims to perform sentiment analysis and evaluate the performance of algorithms in classifying customer reviews on the Indonesian e-commerce platform, Tokopedia, using the Support Vector Machine (SVM) algorithm and Adaptive Synthetic Sampling (ADASYN). The SVM algorithm was chosen for its ability to handle complex classification problems, while the ADASYN technique was employed to address the imbalance between the majority and minority classes in the dataset, which consists of 2,819 negative reviews and 450 positive reviews. The results show that the combination of the SVM and ADASYN algorithms have the highest accuracy with an accuracy rate of 93.7%, a recall of 76.6%, and an f1-score of 79%. Keywords : Adaptive Synthethic Sampling, algorithm, dataset, Sentiment analysis, Support Vector Machine.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407004011	T149444	T1494442024	Central Library (REFERENCES)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1494442024

Publisher

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

Collation

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

Language

Indonesia

ISBN/ISSN

-

Classification

519.50

Content Type

Text

Media Type

unmediated

Carrier Type

unspecified

Edition

-

Subject(s)

Prodi Teknik Informatika
Adaptive Synthethic Sampling

Specific Detail Info

-

Statement of Responsibility

UIN YOLA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment