Salwa Ziada Salsabiila, . (2023) PERBANDINGAN TEKNIK PEMBOBOTAN FAST TEXT DAN WORD2VEC UNTUK DETEKSI MULTICLASS EMOSI MENGGUNAKAN METODE CONV-LSTM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
Abstrak.pdf Download (13kB) |
|
Text
Awal.pdf Download (493kB) |
|
Text
BAB I.pdf Download (167kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (566kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (506kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (678kB) |
|
Text
BAB V.pdf Download (37kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (176kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (89kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (953kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (953kB) |
|
Text
Artikel KI.pdf Restricted to Repository staff only Download (620kB) |
Abstract
Emotions are one aspect of human psychology which includes the ability to control a feeling and behavior that creates a way of self-expression that is in line with the environment. The source of data collection in processing the emotion detection process with text comes from social media Twitter. Solving the problem of how to compare the embedding weighting techniques of Fast Text and Word2Vec with the combination of Conv-LSTM to the emotion detection text classification process and how the results of the performance analysis are. This study aims to implement and obtain the results of performance analysis in a comparison of the Fast Text and Word2Vec algorithms. The method used is a combination of the Convolutional Neural Network CNN and Long Short Term Memory (LSTM) methods, which are then referred to as Conv-LSTM for the text classification process for detecting labels on sentiment analysis research objects regarding Mr. Anies Rasyid Baswedan's keywords based on 98,664 data tweets from social Twitter media with 6 multiclass classifications, namely happy, sad, angry, disgusted, surprised, and afraid. The highest accuracy results using the Word2Vec Skipgram method with a Max Pooling of 0.8499.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910511094] [Pembimbing 1: Helena Nurramdhani Irmanda] [Pembimbing 2: Artika Arista] [Penguji 1: Yuni Widiastiwi] [Penguji 2: Jayanta] |
| Uncontrolled Keywords: | Emotion Detection, Conv-LSTM, Word2Vec, Fast Text, Twitter |
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Salwa Ziada Salsabiila |
| Date Deposited: | 28 Jul 2023 07:10 |
| Last Modified: | 31 Dec 2023 16:23 |
| URI: | http://repository.upnvj.ac.id/id/eprint/25098 |
Actions (login required)
 |
View Item |