2022
DOI: 10.2196/35115
|View full text |Cite
|
Sign up to set email alerts
|

Monitoring User Opinions and Side Effects on COVID-19 Vaccines in the Twittersphere: Infodemiology Study of Tweets

Abstract: Background In the current phase of the COVID-19 pandemic, we are witnessing the most massive vaccine rollout in human history. Like any other drug, vaccines may cause unexpected side effects, which need to be investigated in a timely manner to minimize harm in the population. If not properly dealt with, side effects may also impact public trust in the vaccination campaigns carried out by national governments. Objective Monitoring social media for the ea… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
14
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 15 publications
(15 citation statements)
references
References 41 publications
1
14
0
Order By: Relevance
“…In previous work, several custom algorithms were proposed, such as (1) deep learning with a CamemBERT model [ 28 ], BERT [ 46 , 47 ], RoBERTa [ 48 ], FastText [ 49 ], convolutional neural network–long short-term memory with word2vec embeddings [ 50 ] or (2) machine learning with naïve Bayes [ 51 ] or decision tree [ 52 ] models. Off-the-shelf sentiment analysis models include Amazon Web Services Comprehend sentiment analysis [ 53 ] and VADER [ 54 - 60 ], which is a Python lexicon and rule-based sentiment analysis tool [ 43 ].…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…In previous work, several custom algorithms were proposed, such as (1) deep learning with a CamemBERT model [ 28 ], BERT [ 46 , 47 ], RoBERTa [ 48 ], FastText [ 49 ], convolutional neural network–long short-term memory with word2vec embeddings [ 50 ] or (2) machine learning with naïve Bayes [ 51 ] or decision tree [ 52 ] models. Off-the-shelf sentiment analysis models include Amazon Web Services Comprehend sentiment analysis [ 53 ] and VADER [ 54 - 60 ], which is a Python lexicon and rule-based sentiment analysis tool [ 43 ].…”
Section: Discussionmentioning
confidence: 99%
“…Kummervold et al [ 46 ] obtained an F 1 -score of 0.78 to predict the attitude of pregnant women toward vaccination against COVID-19, but the categories for the classification were different. Portelli et al [ 48 ] used a RoBERTa model trained on TweetEval Benchmark. However, the authors only provided the recall for sentiment analysis, which was 72.1, and not the precision, which does not allow a comparison with our results.…”
Section: Discussionmentioning
confidence: 99%
“…Additional machine learning techniques for polarity classification were Microsoft Azure cognitive services, Amazon Web Services (AWS), and Baidu’s AipNLP [ 59 , 64 , 75 ]. Deep learning techniques mainly used convolutional neural networks, recurrent neural networks, bidirectional long short-term memory (LSTM), and Bidirectional Encoder Representations from Transformers [ 63 , 65 , 66 , 68 , 71 , 77 ].…”
Section: Resultsmentioning
confidence: 99%
“…Although public sentiments on COVID-19 vaccines varied significantly over time and geography [ 7 , 33 , 39 ], positive sentiments were more prevalent than negative ones regarding COVID-19 vaccines [ 7 , 19 , 20 , 22 , 25 , 29 , 33 , 41 - 44 , 46 , 47 , 51 , 57 , 60 , 62 , 65 , 70 , 72 , 76 , 78 , 84 , 85 ], with trust and anticipation being the predominant emotions [ 20 , 23 , 32 , 37 , 50 , 54 , 58 ]. However, some other studies found that negative sentiments overwhelmed positive ones, with fear being the dominant emotion [ 53 , 59 , 64 , 66 , 71 , 73 , 79 - 82 , 86 ]. Positive sentiments were found to be mainly related to increased vaccine coverage, vaccine development, vaccination research, and health services [ 31 , 57 , 67 , 69 ], whereas negative sentiments were positively associated with increased COVID-19 cases, misinformation, conspiracy theories, and fear regarding vaccine safety [ 21 , 55 ].…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation