Can Social Media Data Be Utilized to Enhance Early Warning: Retrospective Analysis of the U.S. Covid-19 Pandemic

L, Li; Gao, Lijie; Zhou, Jiayan; Ma, Zihui; Choy, Darren Mun Yoong; Hall, Molly A.

doi:10.1101/2021.04.11.21255285

Cited by 3 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A similar study [51] examines the possibility of leveraging Twitter data to alert the public about the US COVID-19 pandemic. By "crowdsourcing" public opinions, this strategy allows the public and private sectors to timely uncover hazards and prepare for pandemics.…”

Section: A Social Media For Sentiment Analysismentioning

confidence: 99%

“…Some studies have employed manual surveying tools to collect observations that might correlate public awareness with the outbreak variations during a certain period. The authors in [51] have employed NLP and conventional machine learning models to classify tweets contents into "signal" or "not signal", while the first-class indicates that the Twitter user recognizes the COVID-19 outbreak risk in USA. The "signal" tweets volumes were compared to the counts of COVID-19 active cases.…”

Section: Social Media For Temporal Public Awarenessmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

et al. 2022

View full text Add to dashboard Cite

According to the World Health Organization, several factors have affected the accurate reporting of SARS-CoV-2 outbreak status, such as limited data collection resources, cultural and educational diversity, and inconsistent outbreak reporting from different sectors. Driven by this challenging situation, this study investigates the potential expediency of using social network data to develop reliable early information surveillance and warning system for pandemic outbreaks. As such, an enhanced framework of three inherently interlinked subsystems is proposed. The first subsystem includes data collection and integration mechanisms, data preprocessing, and hybrid sentiment analysis tools to identify tweet sentiment taxonomies and quantitatively estimate public awareness. The second subsystem comprises the feature extraction unit that identifies, selects, embeds, and balances feature vectors and the classifier fitting and training unit. This subsystem is designed to capture the most effective linguistic feature combinations with more spatial evidence by using a variety of approaches, including linear classifiers, MLPs, RNNs, and CNNs, as well as pre-trained word embedding algorithms. The last is the modeling and situational awareness evaluation subsystem, which measures temporal associations between pandemic-relevant social network activities and officially announced infection counts in the most hazardous geolocations. The proposed framework was developed and tested using a combination of static datasets and real-time scraped Twitter data. The results of these experiments showed the remarkable performance of the framework in assessing the temporal associations between public awareness and outbreak status. It also showed that the Decision Tree Classifier with Unigram+TF-IDF feature vectors outperformed other conventional models for sentiment classification and geolocation classification with an accuracy of 94.3% and 80.8, respectively. As indicated, conventional machine learning algorithms didn't achieve a precision of more than 80%, while, for instance, MLP with selfembedding layer, Word2Vec, and GloVe pre-trained word embedding resulted in very poor accuracy of 10%, 36%, and 32%, respectively. However, adding the PoS tag one-hot encoding embedding increased the validation accuracy from 36% to approximately 89%, while the best performance for the second subsystem was achieved by Bi-LSTM with RoBERTa word embedding, with an accuracy of 96%. The achieved results reveal that the proposed framework can proactively capture the potential hazards associated with the prevalence of infectious diseases as an effective early detection and info-surveillance awareness system.

show abstract

Section: A Social Media For Sentiment Analysismentioning

confidence: 99%

Section: Social Media For Temporal Public Awarenessmentioning

confidence: 99%

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…As propriedades das redes sociais permitem que os indivíduos divulguem informação e conhecimento, tornando assim possível evocar a consciência pública em larga escala num curto período. Compreender essas informações, opiniões, momento, local e sua disseminação nas redes sociais pode fornecer recursos inestimáveis para alimentar os sistemas de alerta precoce (L. Li et al, 2021).…”

Section: Lista De Figurasunclassified

“…As informações disponíveis nas redes sociais são terreno fértil para a criação de novas ideias para gerar sistemas de alertas precoces em vários cenários. O entendimento das informações online criadas em um determinado lugar e horário são subsídios que podem ser incorporados em sistemas de alertas precoces (L. Li et al, 2021).…”

Section: Redes Sociais E Situações De Calamidade Pandemias E Epidemiasunclassified

“…estudaram a possibilidade de detectar a ocorrência das principais doenças na Indonésia a partir da classificação de posts das redes sociais. Nesse estudo são abordadas formas de identificar o tipo da doença a partir dos tweets e como pode ser visualizada em mapas a disseminação das doenças Li et al (2021). exploram o potencial do uso dos dados da rede social Twitter para melhorar os alertas sobre a pandemia do COVID-19, o trabalho conduz um estudo investigando mais de 14 milhões de tweets postados de 01 janeiro de 2020 a 10 março de 2020.…”

unclassified

See 1 more Smart Citation

Alertas sanitários em cidades inteligentes: artefato para previsão de doenças com base em dados de redes sociais

Santos¹

View full text Add to dashboard Cite

Primeiramente, aos meus pais, José Carlos e Maria das Graças que sempre me apoiaram em todos os meus sonhos e objetivos. Aos meus filhos Gabriel e Eduardo, por despertarem em mim o interesse em cursar o Mestrado e voltar para a academia.A minha querida e amada esposa Lígia, pelo suporte e por me incentivar a sempre ser uma versão melhor a cada dia.A minha orientadora, Profa. Dra. Daielly Melina Nassif Mantovani por todo aprendizado durante a jornada da dissertação, pelas várias conversas pessoais a quem passei a ter como uma amiga.Aos membros da banca de qualificação, Prof.

show abstract

Adapting recurrent neural networks for classifying public discourse on COVID-19 symptoms in Twitter content

et al. 2022

View full text Add to dashboard Cite

The COVID-19 infection, which began in December 2019, has claimed many lives and impacted all aspects of human life. With time, COVID-19 was identified as a pandemic outbreak by the World Health Organization (WHO), putting massive pressure on global health. During this ongoing pandemic, the exponential growth of social media platforms has provided valuable resources for distributing information, as well as a source for self-reported disease symptoms in public discourse. Therefore, there is an urgent need for effective approaches to detect self-reported symptoms or cases in social media content. In this study, we scrapped public discourse on COVID-19 symptoms in Twitter content. For this, we developed a huge dataset of COVID-19 self-reported symptoms and gold-annotated the tweets into four categories: confirmed, death, suspected, and recovered. Then, we use a machine and deep machine learning models, each with its own set of features, such as feature representation. Furthermore, the experimentations were achieved with recurrent neural networks (RNNs) variants and compared their performance with traditional machine learning algorithms. Experimental results report that optimizing the area under the curve (AUC) enhances model performance, and the long short-term memory (LSTM) has the highest accuracy in detecting COVID-19 symptoms in real-time public messaging. Thus, the LSTM classifier in the proposed pipeline achieves a classification accuracy of 90.7%, outperforming existing state-of-the-art algorithms for multi-class classification.

show abstract

Can Social Media Data Be Utilized to Enhance Early Warning: Retrospective Analysis of the U.S. Covid-19 Pandemic

Cited by 3 publications

References 50 publications

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

Alertas sanitários em cidades inteligentes: artefato para previsão de doenças com base em dados de redes sociais

Adapting recurrent neural networks for classifying public discourse on COVID-19 symptoms in Twitter content

Contact Info

Product

Resources

About