Skripsi

KLASIFIKASI SENTIMEN TERHADAP DATA TEXT JEJARING SOSIAL DENGAN TOPIK VAKSIN COVID-19 MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM)

---

Penilaian

---

In August 2020, the government announced it had found a coronavirus vaccine and distributed it to the public to stop the pandemic. This time the government's policy triggered many public reactions in the form of negative and positive sentiments about the vaccine. The greater number of sentiments circulating in the community regarding the ongoing pandemic and the high public enthusiasm for the government's Covid-19 Vaccine policy product this time, the classification of public sentiment towards this vaccine is deemed necessary. Community sentiments are recorded and collected from a social network, namely the Twitter social network where there are many public sentiments on the topic of the Covid-19 Vaccine. The classification of these sentiments will use Natural Language Processing (NLP) & Support Vector Machine (SVM) as the classification method. From the experiments conducted with 80% data split of training data with 20% of test data resulted in the highest Precision, Recall and F1-Score values, while for experiments with 20% data split of training data with 80% of test data yielded Precision, Recall and The lowest F1-Score. Data classification can be carried out properly using the Support Vector Machine method, so that it can create a system that is able to classify sentiments on the topic of the Covid-19 Vaccine. The results of the prediction of sentiment text data using the Support Vector Machine method can be used as consideration or reference for government decision making in making policies regarding the Covid-19 vaccine topic.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002169	T53257	T532572021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T532572021

Publisher

Inderalaya : Fakultas Ilmu komputer, Prodi Sistem Komputer., 2021

Collation

xviii, 85 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.754 07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Situs Jejaring Sosial, Sosial Media
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment