INTI Nusa Mandiri
Vol 18 No 1 (2023): INTI Periode Agustus 2023

OPTIMASI NAIVE BAYES BERBASIS PSO UNTUK ANALISA SENTIMEN PERKEMBANGAN ARTIFICIAL INTELLIGENCE DI TWITTER

Elly Indrayuni (Universitas Bina Sarana Informatika)
Acmad Nurhadi (Universitas Bina Sarana Informatika)



Article Info

Publish Date
04 Aug 2023

Abstract

At present the development of Artificial Intelligence technology is progressing rapidly. There are many new artificial intelligence technologies available in various fields. Artificial Intelligence is an artificial intelligence program that can study data, perform processes of thinking and acting like humans. The presence of Artificial Intelligence technology has many positive impacts, especially in increasing work effectiveness and efficiency. However, AI is also a threat to human resources because slowly human work is being replaced by Artificial Intelligence. Various opinions about the development of Artificial Intelligence are widely discussed on social media such as Twitter. Sentiment analysis is a computational study to automatically categorize opinions into positive or negative categories. In this study, the Naive Bayes algorithm was used to analyze sentiment or public opinion regarding the development of Artificial Intelligence for Twitter users. The data collection method used is crawling data on Twitter. The results of the sentiment classification test for the development of Artificial Intelligence using Naive Bayes yield an accuracy value of 86.42%. Meanwhile, the results of the sentiment classification test using Naive Bayes based on Particle Swarm Optimization (PSO) increased with an accuracy value of 87.55%. Based on the results of this study, the use of PSO as an optimization technique for the Naive Bayes algorithm is proven to be the best algorithm model in sentiment analysis for the development of Artificial Intelligence for English text.

Copyrights © 2023






Journal Info

Abbrev

inti

Publisher

Subject

Computer Science & IT

Description

The INTI Nusa Mandiri Journal is intended as a media for scientific studies on the results of research, thought and analysis-critical studies on the issues of Computer Science, Information Systems and Information Technology, both nationally and internationally. The scientific article in question is ...