COVID-19 Sensing: Negative Sentiment Analysis on Social Media in China via BERT Model

Wang, Tianyi; Ke, Lu; Chow, Kam-Pui; Zhu, Qing

doi:10.1109/access.2020.3012595

Cited by 189 publications

(103 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A model, namely BERT, uses TF-IDF for sentiment analysis and topic modeling for negative posts [ 26 ]. Statistical analysis to detect the presence of pandemic is carried out on tweets of January 2020 [ 27 ].…”

Section: Related Workmentioning

confidence: 99%

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

et al. 2021

View full text Add to dashboard Cite

The spread of Covid-19 has resulted in worldwide health concerns. Social media is increasingly used to share news and opinions about it. A realistic assessment of the situation is necessary to utilize resources optimally and appropriately. In this research, we perform Covid-19 tweets sentiment analysis using a supervised machine learning approach. Identification of Covid-19 sentiments from tweets would allow informed decisions for better handling the current pandemic situation. The used dataset is extracted from Twitter using IDs as provided by the IEEE data port. Tweets are extracted by an in-house built crawler that uses the Tweepy library. The dataset is cleaned using the preprocessing techniques and sentiments are extracted using the TextBlob library. The contribution of this work is the performance evaluation of various machine learning classifiers using our proposed feature set. This set is formed by concatenating the bag-of-words and the term frequency-inverse document frequency. Tweets are classified as positive, neutral, or negative. Performance of classifiers is evaluated on the accuracy, precision, recall, and F1 score. For completeness, further investigation is made on the dataset using the Long Short-Term Memory (LSTM) architecture of the deep learning model. The results show that Extra Trees Classifiers outperform all other models by achieving a 0.93 accuracy score using our proposed concatenated features set. The LSTM achieves low accuracy as compared to machine learning classifiers. To demonstrate the effectiveness of our proposed feature set, the results are compared with the Vader sentiment analysis technique based on the GloVe feature extraction approach.

show abstract

Section: Related Workmentioning

confidence: 99%

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Bidirectional encoder representations from transformers (BERT) is a technique for NLP (natural language processing) pre-training developed by Jacob Devlin and his colleagues from Google [17]. The BERT model has achieved better performance in many sentiments analysis tasks of social media [28][29][30][31][32][33]. For example, in the work of Wang et al [29], the BERT model was used to identify public negative sentiment categories in China regarding COVID-19 on Sina Weibo.…”

Section: Related Workmentioning

confidence: 99%

“…The BERT model has achieved better performance in many sentiments analysis tasks of social media [28][29][30][31][32][33]. For example, in the work of Wang et al [29], the BERT model was used to identify public negative sentiment categories in China regarding COVID-19 on Sina Weibo. In the work of Müller et al [30], the COVID-Twitter-BERT model was a transformer-based model that pre-trained on a large corpus of Twitter messages on the topic of coronavirus disease 2019 (COVID-19).…”

Section: Related Workmentioning

confidence: 99%

Sentiment Analysis Methods for HPV Vaccines Related Tweets Based on Transfer Learning

et al. 2020

View full text Add to dashboard Cite

The widespread use of social media provides a large amount of data for public sentiment analysis. Based on social media data, researchers can study public opinions on human papillomavirus (HPV) vaccines on social media using machine learning-based approaches that will help us understand the reasons behind the low vaccine coverage. However, social media data is usually unannotated, and data annotation is costly. The lack of an abundant annotated dataset limits the application of deep learning methods in effectively training models. To tackle this problem, we propose three transfer learning approaches to analyze the public sentiment on HPV vaccines on Twitter. One was transferring static embeddings and embeddings from language models (ELMo) and then processing by bidirectional gated recurrent unit with attention (BiGRU-Att), called DWE-BiGRU-Att. The others were fine-tuning pre-trained models with limited annotated data, called fine-tuning generative pre-training (GPT) and fine-tuning bidirectional encoder representations from transformers (BERT). The fine-tuned GPT model was built on the pre-trained generative pre-training (GPT) model. The fine-tuned BERT model was constructed with BERT model. The experimental results on the HPV dataset demonstrated the efficacy of the three methods in the sentiment analysis of the HPV vaccination task. The experimental results on the HPV dataset demonstrated the efficacy of the methods in the sentiment analysis of the HPV vaccination task. The fine-tuned BERT model outperforms all other methods. It can help to find strategies to improve vaccine uptake.

show abstract

“…Obtaining accurate, up-to-date information about COVID-19 from social media can help prevent the disease, but fake news can have the opposite effect (Jo et al, 2020;S. Li et al, 2020;Wang et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Accounting for social media effects to improve the accuracy of infection models: combatting the COVID-19 pandemic and infodemic

Bae

Sung

Kwon

2021

European Journal of Information Systems

View full text Add to dashboard Cite

During the COVID-19 pandemic, social media platfforms such as Twitter, Facebook, etc. have played an important role in conveying information, both accurate and inaccurate, thereby creating mass confusion. As the response to COVID-19 has reduced face-to-face contact, communication via social media has increased. Evidence shows that social media affects disease (non-)prevention through the (im)proper distribution of information, and distorts the predictive accuracy of infection models, including legacy Susceptible-Exposed-Infectious-Recovered (SEIR) models. Our adjusted SEIR model reflects the effectiveness of information disseminated through social media by accounting for dimensions of social/informational motivation based on social learning/use and gratification theories, and uses Monte Carlo methodology and computational algorithms to predict effects of social media on the spread of COVID-19 (N = 2,095 cases). The results suggest that social media utilisation measures should be incorporated into SEIR models to improve forecasts of COVID-19 infections. Utilising IS to analyse the spread of digital information via social media platforms can inform efforts to combat the pandemic and infodemic. Agencies responsible for infection and disease control, policy makers, businesses, institutions and educators must accurately monitor infection rates to appropriately allocate funding and human resources and develop effective disease prevention marketing campaigns.

show abstract

COVID-19 Sensing: Negative Sentiment Analysis on Social Media in China via BERT Model

Cited by 189 publications

References 23 publications

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

Sentiment Analysis Methods for HPV Vaccines Related Tweets Based on Transfer Learning

Accounting for social media effects to improve the accuracy of infection models: combatting the COVID-19 pandemic and infodemic

Contact Info

Product

Resources

About