Analysis classification opinion of policy government announces cabinet reshuffle on YouTube comments using 1D convolutional neural networks

Qosim, Ahmad Latif, Kurniawan, Fachrul ORCID: https://orcid.org/0000-0002-3709-8764, Bahruddin, Uril ORCID: https://orcid.org/0000-0001-8599-7281, Mubaraq, Zulfi, Suhartono, Suhartono and Faisal, Muhammad (2021) Analysis classification opinion of policy government announces cabinet reshuffle on YouTube comments using 1D convolutional neural networks. Presented at 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT), 9-11 April 2021, Surabaya, Indonesia.

Text m98214-qosim.pdf Restricted to Repository staff only Download (414kB)

Abstract

YouTube social media has been equipped with a comment column facility so that viewers can comment on YouTube video information in the form of comments or opinions that lead to likes, dislikes, and neutrality. With the increase in the number of viewers, there were also more comments on various writing kinds, both symbolic and numeric. The author wants to take these comments into useful information using sentiment analysis using the 1D Convolutional Neural Networks method. From the results of this study, classification can be done very well with the CNN model and accuracy by using variations of epoch 10, 30, 150, and 300 with the best results of 100%, loss: 1.6%. This study also compared the classification reports for precision, f1-score recall, and accuracy with the Naïve Bayes 93% and CNN methods, with an accuracy of 96%.

Item Type:	Conference (Paper)
Keywords:	Sentiment analysis, Social networking (online), Government, Training data, Writing, Prediction algorithms, Classification algorithms
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Ahmad Latif Qosim
Date Deposited:	29 Jun 2021 10:45

Downloads

Origin of downloads

Actions (login required)

View Item