Sentiment Analysis of Local Community on G20 Performance in Indonesia Using the CNN Deep Learning Algorithm

EasyChair Preprint 9693

Abstract

The G20 Summit Forum was the first time it was held in Indonesia, many local people gave their opinions on the performance given. Given the sentiment or opinion given is quite important for the government as an evaluation material for planning in the future. The method used in this study is the text mining method with deep learning algorithms. The purpose of this study is to analyze the performance sentiment of the G20 Summit by the public using the Convolutional Neural Network (CNN) algorithm to obtain the best model pattern. Testing with a total of 5 kernels and 10 epochs obtained an accuracy value of 96%. In this case it can be proven that the model's ability to classify is considered quite good.

Keyphrases: CNN, Sentiment Analysis, deep learning

@booklet{EasyChair:9693,
  author    = {Hilda Nuraliza and Kusumah Anggraito and Juan Ryanto and Rizka Putri Wahyuni and Muharman Lubis},
  title     = {Sentiment Analysis of Local Community on G20 Performance in Indonesia Using the CNN Deep Learning Algorithm},
  howpublished = {EasyChair Preprint 9693},
  year      = {EasyChair, 2023}}