Open AccessSentiment Analysis on Social Distancing and Physical Distancing on Twitter Social Media using Recurrent Neural Network (RNN) Algorithm
Author(s) -
Fikri Aldi Nugraha,
Nisa Hanum Harani,
Roni Habibi,
Rd. Nuraini Siti Fatonah
Publication year - 2020
Publication title -
join (jurnal online informatika)
Language(s) - English
Resource type - Journals
eISSN - 2528-1682
pISSN - 2527-9165
DOI - 10.15575/join.v5i2.632
Subject(s) - social distance , confusion matrix , recurrent neural network , recall , distancing , computer science , government (linguistics) , confusion , social media , artificial neural network , artificial intelligence , psychology , machine learning , cognitive psychology , covid-19 , medicine , world wide web , linguistics , philosophy , disease , pathology , infectious disease (medical specialty) , psychoanalysis
The government is seeking preventive steps to reduce the risk of the spread of Covid-19, one of which is social restrictions that have become popular with social distancing and physical distancing. One way to assess whether the steps taken by the government regarding social and physical distancing are accepted or not by the community is by conducting sentiment analysis. The process of sentiment analysis is carried out using a variant of the Recurrent Neural Network (RNN), namely Long Short-Term Memory (LSTM). In this study, the results obtained from the sentiment analysis, where the public response to social distancing and physical distancing has more positive sentiments than negative sentiments. To measure the accuracy level of sentiment analysis using the Recurrent Neural Network (RNN) algorithm and evaluation of the modeling is done using confusion matrix where the results obtained for the training dataset are 89% accuracy, 89% recall, 89% precision, and 89% F1 Score. Meanwhile, for the test dataset, an accuracy of 80% was obtained, a recall of 79%, a precision of 81%, and an F1 score of 80%.