Dion Parisda Ray
Universitas Muhammadiyah Prof. Dr. Hamka, Jakarta

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Analisis Sentimen Terhadap KPU 2024 Berdasarkan Tweet Media Sosial Twitter Menggunakan Algoritma Naïve Bayes Dion Parisda Ray; Firman Noor Hasan; Ahmad Rizal Dzikrillah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 4 (2024): Februari 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i4.1587

Abstract

The development of technology is currently very rapid making the dissemination of information faster, the dissemination of information is very easy to get on social media such as Twitter. Twitter social media itself provides features for its users to be able to send and read information in the form of text or video. Elections are a very important moment for the Indonesian people in choosing leaders, in this case the "2024 KPU" as the organizer is expected to be able to run the elections so that they run well. Twitter data collected with the keyword "KPU 2024" obtained a total of 3057 datasets, followed by a cleansing process which produced 715 datasets. The aim of this research is to find out how many positive and negative tweets comments and to indicate the accuracy of the implementation of the Naïve Bayes method. The accuracy results given by the Naïve Bayes algorithm are 67.13% with a precision of 66.04% and a recall of 100.00%. This research was conducted to see public sentiment towards the "2024 KPU" later. Evaluation results in the confusion matrix obtained true positives of 457 and true negatives of 235
Analisis Sentimen Aplikasi Tokocrypto Berdasarkan Ulasan Pada Google Play Store Menggunakan Metode Naïve Bayes Rizki Adi Saputra; Dion Parisda Ray; Faldy Irwiensyah
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 4 (2024): Februari 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i4.1707

Abstract

The development of increasingly sophisticated technology has made many changes and conveniences for humans in all things, including in the financial sector, cryptocurrency has emerged as a form of innovation in the world of finance. A cryptocurrency exchange is an electronic means for carrying out crypto asset trading transactions by sellers or buyers via websites or applications on mobile devices. Currently, many cryptocurrency exchange applications have poor service, security is not guaranteed, withdrawals take quite a long time, expensive admin fees, and other problems, so many Indonesians use reviews on Google Play Store to see user reviews before deciding to use the cryptocurrency exchange application. Many Indonesians are looking for information on cryptocurrency exchange applications that provide the best service for carrying out cryptocurrency buying and selling transactions. One of the cryptocurrency exchange applications that offers this is the Tokocrypto application based on reviews on the Google Play Store. This research aims to understand sentiment towards user reviews on the Tokocrypto application using the Naïve Bayes algorithm method for data classification. The data obtained is review data from February 2024, totaling 2000 reviews from the Google Play Store using Google Collaboratory. This research stage consists of data scraping using web scraping techniques, data labeling, preprocessing, TF-IDF weighting, implementation of the Naïve Bayes algorithm, and evaluation. The clean data obtained was 1000 with a total of 396 positive sentiments and 604 negative sentiments. The results of the sentiment analysis research using the Naïve Bayes algorithm method resulted in an accuracy level of 74.22%, precision of 63.25%, and recall of 81.40%.