An Improved Accuracy in Anticipating the User Nature using a novel logistic regression algorithm throughout the pandemic across online social media based on Indian metrics over Support Vector Clustering Algorithm
5th International Conference on Contemporary Computing and Informatics, IC3I 2022
; : 850-854, 2022.
Article
in English
| Scopus | ID: covidwho-2298292
ABSTRACT
This study's primary goal is to apply machine learning classifier techniques to raise the intensity percentage of user nature detection in order to detect the impact of coronavirus on Twitter users by comparing Novel Logistic Regression and Support Vector Clustering algorithms. Materials and Methods:
The accuracy percentage with a confidence interval of 95% and G-power (value =0.8) was determined many times using the LR method with test size =10 and the SVC algorithm with test size =10. The likelihood that an item belongs to one category or another is predicted using a LR model. Support Vector Clustering algorithm generates a line or hyperplane that divides the data into categories. Results andDiscussion:
LR model has greater efficiency (91%) when compared to Support Vector Clustering (59%). Two groups are numerically unimportant, according to the data obtained with a coefficient of determination of p=0.121 (p>0.05).Conclusion:
LR performs substantially better than the Support Vector Clustering. © 2022 IEEE.
Covid; Novel Logistic Regression; Pandemic; Support Vector Clustering; Twitter; User Nature Detection; Clustering algorithms; Coronavirus; Machine learning; Social networking (online); Vectors; Logistic regression algorithms; Logistics regressions; Support vector clustering algorithm; Test size; Logistic regression
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
5th International Conference on Contemporary Computing and Informatics, IC3I 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS