Deep learning for COVID-19 topic modelling via Twitter: Alpha, Delta and Omicron.
Ontology highlight
ABSTRACT:
SUBMITTER: Lande J
PROVIDER: S-EPMC10393149 | biostudies-literature | 2023
REPOSITORIES: biostudies-literature
Publications
Deep learning for COVID-19 topic modelling via Twitter: Alpha, Delta and Omicron.
Lande Janhavi J Pillay Arti A Chandra Rohitash R
PloS one 20230801 8
Topic modelling with innovative deep learning methods has gained interest for a wide range of applications that includes COVID-19. It can provide, psychological, social and cultural insights for understanding human behaviour in extreme events such as the COVID-19 pandemic. In this paper, we use prominent deep learning-based language models for COVID-19 topic modelling taking into account data from the emergence (Alpha) to the Omicron variant in India. Our results show that the topics extracted f ...[more]
Similar Datasets
Project description:This study investigated the emergence and use of Twitter, as of July 2023 being rebranded as X, as the main forum for social media communication in parasitology. A dataset of tweets was constructed using a keyword search of Twitter with the search terms ‘malaria’, ‘Plasmodium’, ‘Leishmania’, ‘Trypanosoma’, ‘Toxoplasma’ and ‘Schistosoma’ for the period from 2011 to 2020. Exploratory data analyses of tweet content were conducted, including language, usernames and hashtags. To identify parasitology topics of discussion, keywords and phrases were extracted using KeyBert and biterm topic modelling. The sentiment of tweets was analysed using VADER. The results show that the number of tweets including the keywords increased from 2011 (for malaria) and 2013 (for the others) to 2020, with the highest number of tweets being recorded in 2020. The maximum number of yearly tweets for Plasmodium, Leishmania, Toxoplasma, Trypanosoma and Schistosoma was recorded in 2020 (2804, 2161, 1570, 680 and 360 tweets, respectively). English was the most commonly used language for tweeting, although the percentage varied across the searches. In tweets mentioning Leishmania, only ∼37% were in English, with Spanish being more common. Across all the searches, Portuguese was another common language found. Popular tweets on Toxoplasma contained keywords relating to mental health including depression, anxiety and schizophrenia. The Trypanosoma tweets referenced drugs (benznidazole, nifurtimox) and vectors (bugs, triatomines, tsetse), while the Schistosoma tweets referenced areas of biology including pathology, eggs and snails. A wide variety of individuals and organisations were shown to be associated with Twitter activity. Many journals in the parasitology arena regularly tweet about publications from their journal, and professional societies promote activity and events that are important to them. These represent examples of trusted sources of information, often by experts in their fields. Social media activity of influencers, however, who have large numbers of followers, might have little or no training in science. The existence of such tweeters does raise cause for concern to parasitology, as one may start to question the quality of information being disseminated. Graphical abstract Image 1 Highlights • Study of Twitter as the main forum for social media communication in parasitology.• English, Spanish and Portuguese, amongst others, were predominantly the most commonly used languages for tweeting.• Tweeters include citizens, scientists plus a wide range of organisations.• Topics discussed are very domain specific, e.g. Toxoplasma and mental health.• The need for E-Professionalism is discussed.
| S-EPMC10475476 | biostudies-literature
Project description:The article presents a discriminative approach to complement the unsupervised probabilistic nature of topic modelling. The framework transforms the probabilities of the topics per document into class-dependent deep learning models that extract highly discriminatory features suitable for classification. The framework is then used for sentiment analysis with minimum feature engineering. The approach transforms the sentiment analysis problem from the word/document domain to the topics domain making it more robust to noise and incorporating complex contextual information that are not represented otherwise. A stacked denoising autoencoder (SDA) is then used to model the complex relationship among the topics per sentiment with minimum assumptions. To achieve this, a distinct topic model and SDA per sentiment polarity is built with an additional decision layer for classification. The framework is tested on a comprehensive collection of benchmark datasets that vary in sample size, class bias and classification task. A significant improvement to the state of the art is achieved without the need for a sentiment lexica or over-engineered features. A further analysis is carried out to explain the observed improvement in accuracy.
| S-EPMC7924555 | biostudies-literature
Project description:In an effort to gauge the global pandemic's impact on social thoughts and behavior, it is important to answer the following questions: (1) What kinds of topics are individuals and groups vocalizing in relation to the pandemic? (2) Are there any noticeable topic trends and if so how do these topics change over time and in response to major events? In this paper, through the advanced Sequential Latent Dirichlet Allocation model, we identified twelve of the most popular topics present in a Twitter dataset collected over the period spanning April 3rd to April 13th, 2020 in the United States and discussed their growth and changes over time. These topics were both robust, in that they covered specific domains, not simply events, and dynamic, in that they were able to change over time in response to rising trends in our dataset. They spanned politics, healthcare, community, and the economy, and experienced macro-level growth over time, while also exhibiting micro-level changes in topic composition. Our approach differentiated itself in both scale and scope to study the emerging topics concerning COVID-19 at a scale that few works have been able to achieve. We contributed to the cross-sectional field of urban studies and big data. Whereas we are optimistic towards the future, we also understand that this is an unprecedented time that will have lasting impacts on individuals and society at large, impacting not only the economy or geo-politics, but human behavior and psychology. Therefore, in more ways than one, this research is just beginning to scratch the surface of what will be a concerted research effort into studying the history and repercussions of COVID-19.
| S-EPMC9140268 | biostudies-literature
Project description:This paper proposes a new deep learning approach to better understand how optimistic and pessimistic feelings are conveyed in Twitter conversations about COVID-19. A pre-trained transformer embedding is used to extract the semantic features and several network architectures are compared. Model performance is evaluated on two new, publicly available Twitter corpora of crisis-related posts. The best performing pessimism and optimism detection models are based on bidirectional long- and short-term memory networks. Experimental results on four periods of the COVID-19 pandemic show how the proposed approach can model optimism and pessimism in the context of a health crisis. There is a total of 150,503 tweets and 51,319 unique users. Conversations are characterised in terms of emotional signals and shifts to unravel empathy and support mechanisms. Conversations with stronger pessimistic signals denoted little emotional shift (i.e. 62.21% of these conversations experienced almost no change in emotion). In turn, only 10.42% of the conversations laying more on the optimistic side maintained the mood. User emotional volatility is further linked with social influence.
| S-EPMC9758015 | biostudies-literature
Project description:BackgroundVaccination is a cornerstone of the prevention of communicable infectious diseases; however, vaccines have traditionally met with public fear and hesitancy, and COVID-19 vaccines are no exception. Social media use has been demonstrated to play a role in the low acceptance of vaccines.ObjectiveThe aim of this study is to identify the topics and sentiments in the public COVID-19 vaccine-related discussion on social media and discern the salient changes in topics and sentiments over time to better understand the public perceptions, concerns, and emotions that may influence the achievement of herd immunity goals.MethodsTweets were downloaded from a large-scale COVID-19 Twitter chatter data set from March 11, 2020, the day the World Health Organization declared COVID-19 a pandemic, to January 31, 2021. We used R software to clean the tweets and retain tweets that contained the keywords vaccination, vaccinations, vaccine, vaccines, immunization, vaccinate, and vaccinated. The final data set included in the analysis consisted of 1,499,421 unique tweets from 583,499 different users. We used R to perform latent Dirichlet allocation for topic modeling as well as sentiment and emotion analysis using the National Research Council of Canada Emotion Lexicon.ResultsTopic modeling of tweets related to COVID-19 vaccines yielded 16 topics, which were grouped into 5 overarching themes. Opinions about vaccination (227,840/1,499,421 tweets, 15.2%) was the most tweeted topic and remained a highly discussed topic during the majority of the period of our examination. Vaccine progress around the world became the most discussed topic around August 11, 2020, when Russia approved the world's first COVID-19 vaccine. With the advancement of vaccine administration, the topic of instruction on getting vaccines gradually became more salient and became the most discussed topic after the first week of January 2021. Weekly mean sentiment scores showed that despite fluctuations, the sentiment was increasingly positive in general. Emotion analysis further showed that trust was the most predominant emotion, followed by anticipation, fear, sadness, etc. The trust emotion reached its peak on November 9, 2020, when Pfizer announced that its vaccine is 90% effective.ConclusionsPublic COVID-19 vaccine-related discussion on Twitter was largely driven by major events about COVID-19 vaccines and mirrored the active news topics in mainstream media. The discussion also demonstrated a global perspective. The increasingly positive sentiment around COVID-19 vaccines and the dominant emotion of trust shown in the social media discussion may imply higher acceptance of COVID-19 vaccines compared with previous vaccines.
| S-EPMC8244724 | biostudies-literature
Project description:According to the World Health Organization, vaccine hesitancy was one of the ten major threats to global health in 2019, including the COVID-19 vaccine. The availability of vaccines does not always mean utilization. This is because, people have less confidence in vaccines, which resulted in vaccination hesitancy and developing global decline in vaccine intake and has caused viral disease outbreaks worldwide. Therefore, there is a need to understand people's perceptions about the COVID-19 vaccine to help the manufacturing companies of the vaccine to improve their marketing strategy based on the rejection causes. In this paper, we used multi-class Sentiment Analysis to classify people's opinions from extracted tweets about COVID-19 vaccines, using firstly different Machine Learning (ML) classifiers such as Logistic Regression (LR), Stochastic Gradient Descent, Support Vector Machine, K-Nearest Neighbors, Decision Tree (DT), Multinomial Naïve Bayes, Random Forest and Gradient Boosting and secondly various Deep Learning (DL) models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), RNN-LSTM and RNN-GRU. Then, we investigated the analysis of the negative tweets to identify the causes of rejection using the Latent Dirichlet Allocation (LDA) technique. Finally, we classified these negative tweets according to the rejection causes for all the vaccines using the same selected ML and DL models. The result of SA showed that DT gives the best performance with an accuracy of 92.26% and for DL models, GRU achieved 96.83%. Then, we identified five causes: Lack of safety, Side effect, Production problem, Fake news and Misinformation, and Cost. Furthermore, for the classification of the negative tweets according to the identified rejection causes, the LR achieved the best result with an accuracy of 89.97%. For DL models, the LSTM model showed the best result with an accuracy of 91.66%.
| S-EPMC10069356 | biostudies-literature
Project description:ObjectiveCOVID-19 can rarely lead to severe illness in pediatric patients. The aim of this study was to determine if severe outcomes in pediatric COVID-19 have changed over the course of the pandemic.MethodsThis was a multicenter, observational cohort analysis from a large regional healthcare system in metro Detroit using electronic health record data to evaluate emergency visits, hospitalization, and severe COVID-19 disease in pediatric patients. Consecutive pediatric patients presenting to the emergency department with a primary diagnosis of COVID-19 were included. Outcomes data was gathered from three distinct time intervals that coincided with Alpha, Delta, and Omicron variant predominance (Time interval 1 (T1) 1/1/2021-6/30/2021: Alpha, T2 7/1/2021-12/31/2021: Delta, T3 1/1/2022-6/16/2022): Omicron. The primary outcome was severe disease inclusive of composite intensive care unit admission, mechanical ventilation, multisystem inflammatory syndrome in children (MIS-C), myocarditis, or death. Secondary outcomes included severe outcomes considering viral coinfection and vaccination status.ResultsBetween 1/1/2021 and 6/16/2022, there were 4517 emergency COVID-19 visits, of which 12.5% (566) of children were hospitalized. 24.4% (138), 31.6% (179), and 44.0% (249) of admissions occurred during T1, T2 and T3 respectively. Most patients were male (55.1%) and 59.9% identified as Caucasian. The median age was 5.0 (interquartile range 1.0, 13.0) with infants comprising 22.8% (129), toddlers 25.1% (142), children 23.0% (130), and teenagers 29.2% (165). Over the course of the pandemic, the proportion of infants in hospitalization increased from 16.7% in T1 to 19.6% in T2 to 28.5% in T3 (p < 0.01) while the proportion of teenagers in hospitalization decreased from 39.1% in T1 to 31.3% in T2 to 22.1% in T3 (p < 0.001). Oxygen therapy was required in a minority (29.9%) of cases with supplemental oxygen utilized the least in T3 (16.5%) and most in T2 (30.2%). Composite severe disease decreased throughout the pandemic occurring in 36.2% in T1, 27.4% in T2, and 18.9% in T3. A multivariable logistic regression analysis revealed the odds of composite severe disease was significantly lower in T3 compared to T1 (adjusted odds ratio [aOR] 0.35, 95% Confidence Interval 0.21-0.60, p < 0.001). Fully vaccinated or fully vaccinated and boosted admission rates remained low throughout all periods with 4.4% in T1, 4.5% in T2 and 8.4% in T3. Viral coinfection was most common during T2 (16.8%) followed by T3 (12.5%) and least common in T1 (5.1%) (p = 0.006). Coinfection occurred more commonly in younger children with a median age of 1.2 (0.0, 4.5) compared to those with mono-infection with a median age of 6 (1.0, 14.0) (p < 0.001). Severe outcomes occurred in 45.6% of coinfection cases compared to 22.1% without coinfection (p < 0.001).ConclusionsWhile Omicron cases had the highest admission frequency, severe illness was lower than Delta and Alpha variants. Coinfection with respiratory viruses increased the risk of severe outcomes and impacted infants more than older children.FundingNone.
| S-EPMC9714340 | biostudies-literature
Project description:Little information is available regarding incidence and severity of pulmonary embolism (PE) across the periods of ancestral strain, Alpha, Delta, and Omicron variants. The aim of this study is to investigate the incidence and severity of PE over the dominant periods of ancestral strain and Alpha, Delta, and Omicron variants. We hypothesized that the incidence and the severity by proximity of PE in patients with the newer variants and vaccination would be decreased compared with those in ancestral and earlier variants. Patients with COVID-19 diagnosis between March 2020 and February 2022 and computed tomography pulmonary angiogram performed within a 6-week window around the diagnosis (-2 to +4 weeks) were studied retrospectively. The primary endpoints were the associations of the incidence and location of PE with the ancestral strain and each variant. Of the 720 coronavirus disease 2019 patients with computed tomography pulmonary angiogram (58.6 ± 17.2 years; 374 females), PE was diagnosed among 42/358 (12%) during the ancestral strain period, 5/60 (8%) during the Alpha variant period, 16/152 (11%) during the Delta variant period, and 13/150 (9%) during the Omicron variant period. The most proximal PE (ancestral strain vs variants) was located in the main/lobar arteries (31% vs 6%-40%), in the segmental arteries (52% vs 60%-75%), and in the subsegmental arteries (17% vs 0%-19%). There was no significant difference in both the incidence and location of PE across the periods, confirmed by multivariable logistic regression models. In summary, the incidence and severity of PE did not significantly differ across the periods of ancestral strain and Alpha, Delta, and Omicron variants.
| S-EPMC10695578 | biostudies-literature
Project description:India locked down 1.3 billion people on March 25, 2020, in the wake of COVID-19 pandemic. The economic cost of it was estimated at USD 98 billion, while the social costs are still unknown. This study investigated how government formed reactive policies to fight coronavirus across its policy sectors. Primary data was collected from the Press Information Bureau (PIB) in the form press releases of government plans, policies, programme initiatives and achievements. A text corpus of 260,852 words was created from 396 documents from the PIB. An unsupervised machine-based topic modelling using Latent Dirichlet Allocation (LDA) algorithm was performed on the text corpus. It was done to extract high probability topics in the policy sectors. The interpretation of the extracted topics was made through a nudge theoretic lens to derive the critical policy heuristics of the government. Results showed that most interventions were targeted to generate endogenous nudge by using external triggers. Notably, the nudges from the Prime Minister of India was critical in creating herd effect on lockdown and social distancing norms across the nation. A similar effect was also observed around the public health (e.g., masks in public spaces; Yoga and Ayurveda for immunity), transport (e.g., old trains converted to isolation wards), micro, small and medium enterprises (e.g., rapid production of PPE and masks), science and technology sector (e.g., diagnostic kits, robots and nano-technology), home affairs (e.g., surveillance and lockdown), urban (e.g. drones, GIS-tools) and education (e.g., online learning). A conclusion was drawn on leveraging these heuristics are crucial for lockdown easement planning.
| S-EPMC7485898 | biostudies-literature
Project description:BACKGROUND:The paper introduces a deep learning-based approach for real-time detection and insights generation about one of the most prevalent chronic conditions in Australia - Pollen allergy. The popular social media platform is used for data collection as cost-effective and unobtrusive alternative for public health monitoring to complement the traditional survey-based approaches. METHODS:The data was extracted from Twitter based on pre-defined keywords (i.e. 'hayfever' OR 'hay fever') throughout the period of 6 months, covering the high pollen season in Australia. The following deep learning architectures were adopted in the experiments: CNN, RNN, LSTM and GRU. Both default (GloVe) and domain-specific (HF) word embeddings were used in training the classifiers. Standard evaluation metrics (i.e. Accuracy, Precision and Recall) were calculated for the results validation. Finally, visual correlation with weather variables was performed. RESULTS:The neural networks-based approach was able to correctly identify the implicit mentions of the symptoms and treatments, even unseen previously (accuracy up to 87.9% for GRU with GloVe embeddings of 300 dimensions). CONCLUSIONS:The system addresses the shortcomings of the conventional machine learning techniques with manual feature-engineering that prove limiting when exposed to a wide range of non-standard expressions relating to medical concepts. The case-study presented demonstrates an application of 'black-box' approach to the real-world problem, along with its internal workings demonstration towards more transparent, interpretable and reproducible decision-making in health informatics domain.
| S-EPMC6839169 | biostudies-literature