Skripsi

ANALISIS SENTIMEN ULASAN PRODUK BERBAHASA INDONESIA MENGGUNAKAN DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK DAN WORD2VEC

---

Penilaian

---

The phenomenon of electronic commerce arises as a result of the rapid development of technology and communication media. Product reviews are important information for users of electronic commerce media, but reviews are often written incorrectly. The Deep Learning method is a method that is developing very rapidly at this time. We used the Convolutional Neural Network method with the Word2Vec feature to carry out a sentiment analysis of 5,080,101 reviews. Probability of Similarity will be used as an additional pre-processing process to determine the effect of the corrected word on the model being trained. Based on the test results, the model shows excellent performance with an accuracy of 0.91119, a precision of 0.91123, a recall of 0.91232, and an F1-score of 0.91178. The performance of the model with the normalization stage which has quite good performance compared to the stemming and stopword removal stages. The stages of word improvement using the Probability of Similarity method improve 4 out of 5 data schemes, but with large enough training data this process is considered to be quite time consuming and resource consuming.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307004898	T126981	T1269812023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1269812023

Publisher

Inderalaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xvi, 98 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

003.07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Jurusan Teknik Informatika
Sistem analisis

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment