Covid-19 vaccination: An attitude analysis of global users of social media towards government communication. (Record no. 526731)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01941nam a22001457a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 240621b ||||| |||| 00| 0 eng d |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Singh, Ajay Kumar et al |
| 245 ## - TITLE STATEMENT | |
| Title | Covid-19 vaccination: An attitude analysis of global users of social media towards government communication. |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication, distribution, etc | Indian Journal of Public Administration |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 70(2), Jun, 2024: p,.318-331 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc | Amidst a global pandemic, the key challenge before governments, health institutions and administrative authorities is to communicate and inform the general public about the never-heard of morbidity, virology and immunity in their simplest form and language. However, this can only be possible when they can appropriately predict the perceptions and reactions of public to a given set of communications regarding the disease, preventive measures and the adoption of established principles of users’ perceptions. This article is a study of the users’ perceptions about Covid-19 vaccination. It conducts sentiment analysis in Python on a dataset of global users of the social media channel Twitter. The dataset available at kaggle.com, comprising 51,393 tweets from December 2020 to February 2021 with more than fifteen features, was put to test. The majority of the people (60.8%) expressed their neutral sentiments towards vaccination, while 23.9% had a positive opinion. Further, in order to evaluate the aforementioned analysis, the machine learning pipeline process of model evaluation is also performed. This process includes a split of dataset into training and testing, followed by determining various evaluation parameters including confusion matrix, precision, recall and F1-score. The accuracy of 97.1% depicts the outperformance of the model.- Reproduced https://journals.sagepub.com/doi/full/10.1177/00195561231221805 |
| 773 ## - HOST ITEM ENTRY | |
| Main entry heading | Indian Journal of Public Administration |
| 906 ## - LOCAL DATA ELEMENT F, LDF (RLIN) | |
| Subject DIP | PANDEMIC |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Item type | Articles |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Permanent location | Current location | Date acquired | Serial Enumeration / chronology | Barcode | Date last seen | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Indian Institute of Public Administration | Indian Institute of Public Administration | 2024-06-21 | 70(2), Jun, 2024: p,.318-331 | AR132306 | 2024-06-21 | Articles |