Covid-19 Vaccine Sentiment Analysis During Second Wave in India by Transfer Learning Using XLNet

Bansal, Anmol; Susan, Seba; Choudhry, Arjun; Sharma, Anubhav

doi:10.1007/978-3-031-09282-4_37

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like BERT, pre-trained XLNet models can also be used for many other downstream tasks while also increasing the limits for sequences. In a recent work, the XLNet transformer was used successfully for the sentiment analysis of unlabeled Covid-19 tweets by transfer learning [7]. The XLNet transformer was pre-trained on US Airlines tweet data set that was unconnected with Covid-19.…”

Section: Pre-trained Transformer Models For Domain-specific Tasksmentioning

confidence: 99%

Adaptation of Domain-Specific Transformer Models With Text Oversampling for Sentiment Analysis of Social Media Posts on Covid-19 Vaccine

Bansal¹,

Choudhry²,

Sharma³

et al. 2023

csci

View full text Add to dashboard Cite

Covid-19 has spread across the world and many different vaccines have been developed to counter its surge. To identify the correct sentiments associated with the vaccines from social media posts, this paper aims to fine-tune pre-trained transformer models on tweets associated with different Covid vaccines, specifically RoBERTa, XLNet and BERT which are recently introduced state-of-the-art bi-directional transformer models, and domain-specific transformer models BERTweet and CT-BERT that are pre-trained on Covid-19 tweets. We further explore the option of data augmentation by text oversampling using LMOTE to improve the accuracies of these models, specifically, for small sample datasets where there is an imbalanced class distribution among the positive, negative and neutral sentiment classes. Our results summarize our findings on the suitability of text oversampling for imbalanced, small sample datasets that are used to fine-tune state-of-the-art pre-trained transformer models, and the utility of having domain-specific transformer models for the classification task.

show abstract

Section: Pre-trained Transformer Models For Domain-specific Tasksmentioning

confidence: 99%