The world has to face health concerns due to huge spread of COVID. For this reason, the development of vaccine is the need of hour. The higher vaccine distribution, the higher the immunity against coronavirus. Therefore, there is a need to analyse the people’s sentiment for the vaccine campaign. Today, social media is the rich source of data where people share their opinions and experiences by their posts, comments or tweets. In this study, we have used the twitter data of vaccines of COVID and analysed them using methods of artificial intelligence and geo-spatial methods. We found the polarity of the tweets using the TextBlob() function and categorized them. Then, we designed the word clouds and classified the sentiments using the BERT model. We then performed the geo-coding and visualized the feature points over the world map. We found the correlation between the feature points geographically and then applied hotspot analysis and kernel density estimation to highlight the regions of positive, negative or neutral sentiments. We used precision, recall and F score to evaluate our model and compare our results with the state-of-the-art methods. The results showed that our model achieved 55% & 54% precision, 69% & 85% recall and 58% & 64% F score for positive class and negative class respectively. Thus, these sentimental and spatial analysis helps in world-wide pandemics by identify the people’s attitudes towards the vaccines.

Sentimental and spatial analysis of COVID-19 vaccines tweets / Umair, A.; Masciari, E.. - In: JOURNAL OF INTELLIGENT INFORMATION SYSTEMS. - ISSN 1573-7675. - (2022), pp. 1-21. [10.1007/s10844-022-00699-4]

Sentimental and spatial analysis of COVID-19 vaccines tweets

Umair A.
Primo
;
Masciari E.
2022

Abstract

The world has to face health concerns due to huge spread of COVID. For this reason, the development of vaccine is the need of hour. The higher vaccine distribution, the higher the immunity against coronavirus. Therefore, there is a need to analyse the people’s sentiment for the vaccine campaign. Today, social media is the rich source of data where people share their opinions and experiences by their posts, comments or tweets. In this study, we have used the twitter data of vaccines of COVID and analysed them using methods of artificial intelligence and geo-spatial methods. We found the polarity of the tweets using the TextBlob() function and categorized them. Then, we designed the word clouds and classified the sentiments using the BERT model. We then performed the geo-coding and visualized the feature points over the world map. We found the correlation between the feature points geographically and then applied hotspot analysis and kernel density estimation to highlight the regions of positive, negative or neutral sentiments. We used precision, recall and F score to evaluate our model and compare our results with the state-of-the-art methods. The results showed that our model achieved 55% & 54% precision, 69% & 85% recall and 58% & 64% F score for positive class and negative class respectively. Thus, these sentimental and spatial analysis helps in world-wide pandemics by identify the people’s attitudes towards the vaccines.
2022
Sentimental and spatial analysis of COVID-19 vaccines tweets / Umair, A.; Masciari, E.. - In: JOURNAL OF INTELLIGENT INFORMATION SYSTEMS. - ISSN 1573-7675. - (2022), pp. 1-21. [10.1007/s10844-022-00699-4]
File in questo prodotto:
File Dimensione Formato  
umair2022.pdf

solo utenti autorizzati

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 2.62 MB
Formato Adobe PDF
2.62 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/903285
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? ND
social impact