Muhammad, Hisyam (2021) KLASIFIKASI EMOSI PADA TEKS MENGGUNAKAN METODE RECCURENT NEURAL NETWORK. Other thesis, UNIVERSITAS PEMBANGUNAN NASIONAL “VETERAN” YOGYAKARTA.
![[thumbnail of abstrak.pdf]](http://eprints.upnyk.ac.id/style/images/fileicons/text.png) |
Text
abstrak.pdf Download (559kB) |
|
Text
judul.pdf Download (264kB) |
|
Text
daftar isi.pdf Download (872kB) |
|
Text
lembar pengesahan1.pdf Download (395kB) |
Abstract
isconceptions in reading online chat text messages often
occur in the era of technology 4.0. From this
misunderstanding, it often becomes an argument. Research
on the classification of emotions in text is a solution to
overcome misunderstandings in replying to messages on
online chatting media. In examining emotions in text,
especially in online text chatting. There are several
differences from text in general, such as abnormal
vocabulary, incompatible syntax structure. The solution to
this problem is to carry out the text processing stage during
the text classification process. Like preprocessing word
normalization, extracting full sentence features. This study
uses artificial intelligence with the Recurrent Neural
Network method with Long Short Term Memory
architecture. The dataset used in this study is the ISEAR
dataset and data taken from the questionnaire. The results
of the accuracy of the bot's accuracy in classifying emotions
amounted to 91% of the 7521 data. These results were
obtained from bot training with training data of 70% and
test data of 30% of the entire dataset. Meanwhile, the
accuracy of the test results with 10 respondents resulted in
an accuracy of 65%
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Emotion Classification; Machine Learning; Recurrent Neural Network; Long Short Term Memory; Text Classification |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science |
| Depositing User: | Nurul Alifah Rahmawati |
| Date Deposited: | 20 Apr 2022 02:34 |
| Last Modified: | 20 Apr 2022 02:34 |
| URI: | http://eprints.upnyk.ac.id/id/eprint/29568 |
Actions (login required)
 |
View Item |