Analyzing the Sentiments by Classifying the Tweets Based on COVID-19 Using Machine Learning Classifiers
2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society, TRIBES 2021
; 2021.
Article
in English
| Scopus | ID: covidwho-1831872
ABSTRACT
In the current scenario, almost all the countries face one of the biggest disasters in COVID-19. This paper has to analyze the tweets related to COVID 19 and discuss the various machine learning algorithms and their performance analysis on the tweets associated with COVID-19. The implemented classification algorithms are applied to classify the sentiments to predict whether they relate to COVID-19 or non-COVID-19. Ten most popular classification algorithms implemented. The Linear Support Vector Machine (LSVM) achieved the highest test accuracy in these algorithms with 90.3%. Logistic regression has performed better in recall with 96.06%, F1 score of 90.46%, ROC_AUC with 90.48%. Random forest classifier has achieved the better specificity and precision of 99.16% and 96.3%, respectively. Out of all, stochastic gradient descent (SGD) has attained better results in all the computational parameters. © 2021 IEEE.
COVID-19; explainable ai; Naïve Bayes; stochastic gradient descent; Twitter; Decision trees; Gradient methods; Learning algorithms; Logistic regression; Support vector machines; 'current; Classification algorithm; Linear Support Vector Machines; Machine learning algorithms; Naive bayes; Performances analysis; Test accuracy; Stochastic systems
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society, TRIBES 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS