Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
Muhyiddin, Sulthon
Unknown Affiliation
Computer Science & IT Education

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
SENTIMENT ANALYSIS OF PUBLIC OPINION ON APPLICATION X (TWITTER) IN INDONESIA AGAINST CHATGPT USING NAÏVE BAYES ALGORITHM Sari, Yayak Kartika; Rozi, Fahrur; Muhyiddin, Sulthon; Sukmana, Farid
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.7052

Abstract

In the era of technological development and information is increasingly widespread. Data and information are easier to obtain using current technology, especially using social media such as Instagram, Facebook, (x) Twitter and others. In social media, information can be in the form of public opinions containing praise, hate speech, and hoaxes which can result in arguments against the information presented, especially on the x (twitter) application. Therefore, research was conducted on sentiment analysis of positive and negative opinions of Indonesian people on application x (twitter) about ChatGPT using the naive bayes method. Basically, Naive Bayes looks for the largest conditional probability value for each class. The technique used to explore public opinion data on application x (twitter) about ChatGPT is google collabs with the results of data mining as much as 1012 data. of these 1012 data cleaning and sentiment analysis using the naive bayes method. Naïve Bayes method classification results with a total of 762 twitter comments about ChatGPT. 100 are used as training data modeled using the naïve bayes method. The accuracy value is 99.00%, positive prediction precision is 100%, negative prediction precision is 96.43%, positive data recall is 98.63%, and negative data recall is 100%.
Co-Authors Fahrur Rozi Farid Sukmana, Farid Sari, Yayak Kartika