SENTIMENT ANALYSIS COVID VACCINE ON TWITTER USING SVM ALGORITHM

RETA, RATNA AKILA (2022) SENTIMENT ANALYSIS COVID VACCINE ON TWITTER USING SVM ALGORITHM. Other thesis, Universitas Katholik Soegijapranata Semarang.

[img] Text
17.K1.0027-RATNA AKILA RETA_COVER_a.pdf
Download (522kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB I_a.pdf
Download (115kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB II_a.pdf
Restricted to Registered users only
Download (119kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB III_a.pdf
Download (116kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB IV_a.pdf
Download (213kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB V_a.pdf
Download (436kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_BAB VI_a.pdf
Download (110kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_DAPUS_a.pdf
Download (179kB)
[img] Text
17.K1.0027-RATNA AKILA RETA_LAMP_a.pdf
Download (453kB)

Abstract

Currently there are still many people who have not been vaccinated. many people comment on social media, especially the twitter application, to provide opinions and comments about the covid vaccine in Indonesia. In order to find out the tweets that appeared including positive comments or negative comments, an analysis was carried out to find out how many negative and positive comments were by sentiment analysis. This study analyzes comments taken from the twitter application using the crawling method. Furthermore, pre-processing will be carried out such as case folding, tokenization, and stopword filtering. Then before the classification is carried out, data labeling and data split will be carried out to facilitate classification. After that, classification will be carried out using the SVM algorithm method. The final result of this research project is that there are 9981 data obtained from the crawling method. This data proves that 92.4% of Indonesians gave a neutral response to the topic of the Covid vaccine on the Twitter application. The SVM algorithm is easy to use in the implementation of sentiment analysis. And the accuracy results obtained using the SVM method are 90.5%.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: mr AM. Pudja Adjie Sudoso
Date Deposited: 23 Mar 2022 03:19
Last Modified: 23 Mar 2022 03:19
URI: http://repository.unika.ac.id/id/eprint/28251

Actions (login required)

View Item View Item
Unika Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.