Sentiment Analysis of Public Reaction to COVID19 in Twitter Media using Naïve Bayes Classifier
Djoko Adi Widodo, FT P Teknik Elektro (2021) Sentiment Analysis of Public Reaction to COVID19 in Twitter Media using Naïve Bayes Classifier. In: 1 IEEE International Conference on Health, Instrumentation & Measurement, and Natural Sciences (InHeNce).
PDF
- Published Version
Download (1MB) |
|
PDF
- Published Version
Download (1MB) |
Abstract
Currently, the world's attention was focused on the disease outbreak, namely the corona virus (COVID19). World Health Organization (WHO) declare that this virus was a global pandemic in all countries. The various impacts that arise due to this virus cover various fields, namely health, social, political, religious, economic to resilience and security. Some of the services currently used were still focused on the health sector, namely in the form of treatment and information services related to the development of the spread of the virus. This research will develop a service that was used to identify social impacts in the community through observing community activities on social media, namely Twitter, in the form of an analysis of the public's reaction to COVID19. Through this Twitter, a data acquisition process will be carried out to obtain data related to COVID19 which will then be carried out a sentiment analysis using the Naïve Bayes method so that the results of the public reaction sentiment will be obtained. The experimental result shows that prediction accuracy was 0,86. Furthermore, the results of the Recall was 0,687, the precision was 0,827 and the F-Score was 0.749
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Uncontrolled Keywords: | —Sentiment Analysis, Twitter, Covid19, Naïve Bayes |
Subjects: | T Technology > TK Electrical and Electronic Engineering |
Fakultas: | Fakultas Teknik > Pendidikan Teknik Elektro, S1 |
Depositing User: | mahargjo hapsoro adi |
Date Deposited: | 25 May 2023 07:23 |
Last Modified: | 25 May 2023 07:23 |
URI: | http://lib.unnes.ac.id/id/eprint/58779 |
Actions (login required)
View Item |