Jurnal Sistem Komputer dan Informatika (JSON)
Vol 4, No 4 (2023): Juni 2023

Klasifikasi Sentimen Masyarakat di Twitter Terhadap Ancaman Resesi Ekonomi 2023 dengan Metode Naïve Bayes Classifier

Dea Ropija Sari (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Yusra Yusra (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Muhammad Fikry (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Febi Yanto (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)
Fitri Insani (Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru)



Article Info

Publish Date
02 Jul 2023

Abstract

Economic recession is a condition in which the economic turnover of a country changes to slow or bad that can last for years as a result of the growth of the Gross Domestic Product (GDP) a country decreases over two decades significantly. Early warnings of the emergence of a global recession become a concern for all countries in the world, even global recessions also have a major impact on Indonesia. Such as declining public spending due to decreasing incomes, increasing unemployment, increasing poverty, and many of whom have to accept PHK or salary cuts. Economic strengthening will be important in minimizing these threats, this research needs to be done to see the response of the public to the threat of economic recession. Twitter provides a container to users to comment on the problem of the economy recession 2023 which can be used as sentiment classification information to know positive and negative comments. This research uses the naive bayes classifier algorithm. In this study there are seven main processes, namely data collection, manual labelling, processing, feature weighing (tf-idf), tresholding, naive bayes method classification, testing. From the 1408 comments data on Twitter about the threat of a 2023 economic recession. Based on the results of the classification, using 2 testing models namely data balance and non-balance data obtained the best balance data test results with the highest accuracy result with the process of classification using algortima naïve bayes classifier resulted in accurateness of 78% obtainable by using a comparison of 90% training data and 10% test data.

Copyrights © 2023






Journal Info

Abbrev

JSON

Publisher

Subject

Computer Science & IT Control & Systems Engineering

Description

The Jurnal Sistem Komputer dan Informatika (JSON) is a journal to managed of STMIK Budi Darma, for aims to serve as a medium of information and exchange of scientific articles between practitioners and observers of science in computer. Focus and Scope Jurnal Sistem Komputer dan Informatika (JSON) ...