Social Media Sentiment Analysis using Convolutional Neural Network (CNN) dan Gated Recurrent Unit (GRU)

Adam, Ahmad Zahri Ruhban and Setiawan, Erwin Budi (2023) Social Media Sentiment Analysis using Convolutional Neural Network (CNN) dan Gated Recurrent Unit (GRU). Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), 9 (1). pp. 119-131.

[thumbnail of 11-Social Media Sentiment Analysis using Convolutional Neural Network (CNN) dan Gated Recurrent Unit (GRU).pdf] Text
11-Social Media Sentiment Analysis using Convolutional Neural Network (CNN) dan Gated Recurrent Unit (GRU).pdf

Download (648kB)

Abstract

The advancing technologies are aimed to maximize human performance. One of the great developments in technology is social media. The social media used in this study is Twitter because commonly people in Indonesia give their opinions to the public through tweets. The opinions given are very diverse, where they write positive, negative, and neutral opinions in a large collection of data. Deep learning can be used to automate the process that understands, obtains, and processes the expression of data in the form of text to obtain information from sentiment categories contained in the data. The purpose of this study is to analyze the sentiments of the opinions given by the public in Bahasa Indonesia using deep learning methods and variations in scenarios. To conduct sentiment analysis, tweets are collected by crawling the data. Tweets are then labeled positive, negative, and neutral and then represented as 1, -1, and 0. The method used to classify tweet sentiment is the Convolutional Neural Network (CNN) and Gated Recurrent Unit method (GRU). Research stages include feature selection, feature expansion, preprocessing, and balancing with SMOTE. The highest accuracy value obtained on the CNN-GRU model with an accuracy value of 97.77% value. Based on these tests, it can be concluded that sentiment analysis research on Twitter social media using the combination of Convolutional Neural Network and Gated Recurrent Unit methods can produce fairly high accuracy, and feature expansion testing of the deep learning model paired with SMOTE can provide a significant increase in accuracy values.

Item Type: Artikel Umum
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisi / Prodi: Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Electrical Engineering (S1-Teknik Elektro)
Depositing User: M.Eng. Alfian Ma'arif
Date Deposited: 24 Mar 2023 03:40
Last Modified: 24 Mar 2023 03:40
URI: http://eprints.uad.ac.id/id/eprint/41474

Actions (login required)

View Item View Item