Firsttama, Risav Arrahman (2024) Analisis Sentimen Komentar Video Youtube Konferensi Tingkat Tinggi G20 2022 Menggunakan Metode Naive Bayes dan Support Vector Machine. Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
19082010071-Cover.pdf Download (3MB) | Preview |
|
|
Text (Bab 1)
19082010071-Bab1.pdf Download (59kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Bab 2)
19082010071-Bab2.pdf Restricted to Repository staff only until 22 January 2026. Download (301kB) |
|
|
Text (Bab 3)
19082010071-Bab3.pdf Restricted to Repository staff only until 22 January 2026. Download (204kB) |
|
|
Text (Bab 4)
19082010071-Bab4.pdf Restricted to Repository staff only until 22 January 2026. Download (1MB) |
|
|
Text (Bab 5)
19082010071-Bab5.pdf Download (48kB) | Preview |
|
|
Text (Daftar Pustaka)
19082010071-DaftarPustaka.pdf Download (52kB) | Preview |
|
|
Text (Lampiran)
19082010071-Lampiran.pdf Restricted to Repository staff only until 22 January 2026. Download (544kB) |
Abstract
In the ever-growing digital era, social media, especially YouTube, has become the main source of information that is easily accessed via cell phone. YouTube social media has many users so with the large amount of video media content spread on YouTube there are often positive and negative reviews Irrelevant 2022 G20 Summit. The 2022 G20 Summit Summit addresses global issues such as the global economy and the Covid-19 pandemic so that these reviews give rise to positive or negative sentiments. Sentiment data was obtained using the YouTube API (Application Programming Interface) with 19,103 comment text data to be processed. The data obtained will then be subjected to text preprocessing to clean the text so that it can be executed. Once the data is clean, the next step is to do this automatic labeling using VADER and providing positive or negative values. Sentiment analysis can determine whether a text contains positive or negative opinions using the Naïve Bayes and Support Vector Machine methods. In this research, the Naïve Bayes and Support Vector Machine methods were used by dividing sentiment into two classes, namely, positive and negative, also taking the Confusion Matrix indicator and comparing the Naïve Bayes and Support Vector Machine methods. Based on test results using the Support Vector Machine, the results obtained were a precision value of 92%, recall of 88%, F1-Score of 90%, and accuracy of 90%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T58.6-58.62 Management Information Systems |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Mr. Risav Arrahman Firsttama - | ||||||||||||
| Date Deposited: | 22 Jan 2024 05:53 | ||||||||||||
| Last Modified: | 22 Jan 2024 05:53 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/20489 |
Actions (login required)
 |
View Item |