Marcelina, Marcelina (2022) Analisis persepsi masyarakat Indonesia terhadap vaksin covid-19 dengan metode text mining pada tweets = Perception analysis of Indonesia citizens towards covid-19 vaccine with text mining method on tweets. Bachelor thesis, Universitas Pelita Harapan.
|
Text (Title)
Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (259kB) | Preview |
|
|
Text (Abstract)
Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (477kB) | Preview |
|
|
Text (ToC)
ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (490kB) | Preview |
|
|
Text (Chapter1)
Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (512kB) | Preview |
|
![]() |
Text (Chapter2)
Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (767kB) |
|
![]() |
Text (Chapter3)
Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (614kB) |
|
![]() |
Text (Chapter4)
Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) |
|
![]() |
Text (Chapter5)
Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (466kB) |
|
|
Text (Bibliography)
Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (494kB) | Preview |
|
![]() |
Text (Appendices)
Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB) |
Abstract
Indonesia merupakan negara dengan jumlah kasus COVID-19 terkonfirmasi positif tertinggi di Asia Tenggara. Aturan wajib vaksinasi COVID-19 merupakan langkah pemerintah untuk mengatasi pandemi COVID-19 di Indonesia. Namun, tidak semua masyarakat bersedia untuk divaksin. Dengan menggunakan data tweets mengenai vaksin COVID-19 di Twitter dan metode text mining, akan dilakukan analisis sentimen dan pemodelan topik untuk memahami persepsi masyarakat terhadap vaksin COVID-19. Data yang digunakan adalah tweets bahasa Indonesia pada bulan Mei dan Juni 2021. Analisis sentimen akan menggunakan model Support Vector Machine (SVM), dan pemodelan topik akan menggunakan model Latent Dirichlet Allocation (LDA). Adapun pelabelan sentimen untuk persiapan data latih akan dilakukan dengan manual oleh penulis dan metode leksikon. Tweets akan diklasifikasi menjadi sentimen positif, netral, dan negatif. Eksperimen dilakukan pada model SVM dengan membedakan pelabelan sentimen pada data latih dan data uji, yaitu dengan pelabelan manual dan leksikon. Hasil dari pengujian model SVM menunjukkan bahwa pelabelan sentimen dengan leksikon tidak cocok digunakan untuk persiapan data latih. Selain itu, hasil prediksi sentimen dengan model SVM memperlihatkan bahwa mayoritas tweets mengenai vaksin COVID-19 bersentimen netral. Hasil dari pemodelan topik menunjukkan bahwa masyarakat membahas mengenai ijin penggunaan vaksin, hoaks mengenai vaksin, uji klinis, informasi vaksinasi, dan efek vaksin COVID-19. / Indonesia is the country with the highest number of COVID-19 confirmed cases in Southeast Asia. The mandatory COVID-19 vaccination regulation is a government strategy to overcome the COVID-19 pandemic in Indonesia. However, not all people are willing to be vaccinated. By using tweets data about the COVID-19 vaccine on Twitter and text mining methods, the author conducted sentiment analysis and topic modeling to understand public perceptions towards the COVID-19 vaccine. The data used are Indonesian tweets in May and June 2021. Sentiment analysis used Support Vector Machine (SVM) model, and topic modeling used Latent Dirichlet Allocation (LDA) model. The sentiment labeling for the training data will be done manually by the author and the lexicon method. Tweets will be classified into positive, neutral, and negative sentiment. Experiments were carried out on the SVM model by differentiating the sentiment labeling on training data and test data, namely manual and lexicon labeling. The results of the sentiment analysis showed that labeling sentiments with lexicon is not suitable approach for preparing training data. Furthermore, the sentiment prediction from SVM model showed that most tweets about the COVID-19 vaccine have neutral sentiment. The results of the topic modeling showed that the public discussed about the use permit of vaccines, hoaxes about vaccines, clinical trials, vaccination information, and the effects of COVID-19 vaccines.
Item Type: | Thesis (Bachelor) | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Creators: |
|
||||||||||||
Contributors: |
|
||||||||||||
Uncontrolled Keywords: | vaksin covid-19; analisis sentimen; support vector machine; pemodelan topik; latent dirichlet allocation | ||||||||||||
Subjects: | Q Science > QA Mathematics | ||||||||||||
Divisions: | University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics |
||||||||||||
Depositing User: | Users 6028 not found. | ||||||||||||
Date Deposited: | 23 Feb 2022 03:39 | ||||||||||||
Last Modified: | 23 Feb 2022 03:39 | ||||||||||||
URI: | http://repository.uph.edu/id/eprint/46560 |
Actions (login required)
![]() |
View Item |