OKTAVIAN, TIARA and Abdiansah, Abdiansah and Yusliani, Novi (2022) PENERAPAN SELF-ATTENTIVE NETWORK PADA PENDETEKSIAN CLICKBAIT DI JUDUL BERITA ONLINE INDONESIA. Undergraduate thesis, Sriwijaya University.
![[thumbnail of RAMA_55201_09021281722059.pdf]](http://repository.unsri.ac.id/style/images/fileicons/text.png) |
Text
RAMA_55201_09021281722059.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) |
|
Text
RAMA_55201_09021281722059_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) |
Preview |
Text
RAMA_55201_09021281722059_0001108401_0008118205_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (329kB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (272kB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (335kB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (57kB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_07_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (192kB) |
|
Text
RAMA_55201_09021281722059_0001108401_0008118205_08_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (174kB) |
Abstract
Clickbait is a term that describes a title with the aim of attracting the reader's interest by using flashy and provocative word choices. The problem faced if clickbait detection is done manually is that it takes a long time to be done, because it has to compare the content of the news by reading a whole news for each news title. This study intends to developed software that can detect whether a given news title is clickbait or not by using the self-attentive network method. The data used in this study were 6000 for training data and 2000 for test data. The data will enter the preprocessing stage before going to the self-attentive network. The data were trained using 10-fold Cross Validation. Based on the results of the test data, the model with the best performance is in the 4th fold with precision, recall, and f1-score values of 0.8057, 0.7960, and 0.8008. So that the accuracy value is 0.8020.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | Clickbait, self-attentive network, berita, cross validation |
| Subjects: | Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T175-178 Industrial research. Research and development > T175 General works |
| Divisions: | 09-Faculty of Computer Science > 55201-Informatics (S1) |
| Depositing User: | Tiara Oktavian |
| Date Deposited: | 18 Jan 2023 08:21 |
| Last Modified: | 18 Jan 2023 08:21 |
| URI: | http://repository.unsri.ac.id/id/eprint/86890 |
Actions (login required)
 |
View Item |