Classification aware neural topic model for COVID-19 disinformation categorisation.
Ontology highlight
ABSTRACT:
SUBMITTER: Song X
PROVIDER: S-EPMC7891716 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
Classification aware neural topic model for COVID-19 disinformation categorisation.
Song Xingyi X Petrak Johann J Jiang Ye Y Singh Iknoor I Maynard Diana D Bontcheva Kalina K
PloS one 20210218 2
The explosion of disinformation accompanying the COVID-19 pandemic has overloaded fact-checkers and media worldwide, and brought a new major challenge to government responses worldwide. Not only is disinformation creating confusion about medical science amongst citizens, but it is also amplifying distrust in policy makers and governments. To help tackle this, we developed computational methods to categorise COVID-19 disinformation. The COVID-19 disinformation categories could be used for a) focu ...[more]
Similar Datasets
Project description:MotivationRecent initiatives for federal grant transparency allow direct knowledge extraction from large volumes of grant texts, serving as a powerful alternative to traditional surveys. However, its computational modeling is challenging as grants are usually multifaceted with constantly evolving topics.ResultsWe propose Turtling, a time-aware neural topic model with three unique characteristics. First, Turtling employs pretrained biomedical word embedding to extract research topics. Second, it leverages a probabilistic time-series model to allow smooth and coherent topic evolution. Lastly, Turtling leverages additional topic diversity loss and funding institute classification loss to improve topic quality and facilitate funding institute prediction. We apply Turtling on publicly available NIH grant text and show that it significantly outperforms other methods on topic quality metrics. We also demonstrate that Turtling can provide insights into research topic evolution by detecting topic trends across decades. In summary, Turtling may be a valuable tool for grant text analysis.Availability and implementationTurtling is freely available as an open-source software at https://github.com/aicb-ZhangLabs/Turtling.
| S-EPMC11216609 | biostudies-literature
Project description:It is critical to accurately predict the future popularity of information cascades for many related applications, such as online opinion warning or academic influence evaluation. Despite many efforts devoted to developing effective prediction approaches, especially the recent presence of deep learning-based model, the structural information of the cascade network is ignored. Thus, to make use of the structural information in cascade prediction task, we propose a structural-topic aware deep neural networks (STDNN), which firstly learns the structure topic distribution of each node in the cascade, feeds it to a sequential neural network, and finally predicts the future popularity of the cascades. It can inherit the high interpretability of Hawkes process and possesses the high predictive power of deep learning methods, bridging the gap between prediction and understanding of information cascades by capturing indicative graph structures. We evaluate our model through quantitative experiments, where our model exhibits promising performance, efficiency higher than the baselines.
| S-EPMC10909194 | biostudies-literature
Project description:ObjectivesIn the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model's results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals.MethodsIn this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image.ResultsOur model achieved accuracy of 90.3%, (95% CI: 86.3-93.7%) specificity of 90% (95% CI: 84.3-94%), and sensitivity of 90.5% (95% CI: 85-94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93-0.97).ConclusionWe provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19.Key points• A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%. • A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model's image embeddings.
| S-EPMC8164481 | biostudies-literature
Project description:BackgroundMis/disinformation has reached an epidemic level with the COVID-19 virus and can be largely attributed to the growing digitalization of information and its rapid transmission via social media. Approximately 96% of Canadians and 80% of Americans report encountering COVID-19 dis/misinformation on at least one social media site/app. COVID-19 dis/misinformation promotes scepticism and a lack of confidence in COVID-19 interventions. Black people have been disproportionately affected by the COVID-19 pandemic in terms of negative impacts on their livelihoods and are also more likely to be hesitant to receive the COVID-19 vaccine. Dis/misinformation contributes to high rates of COVID-19 infection and low uptake of COVID-19 vaccination. Hence, the purpose of this scoping review was to map out the nature and extent of current research on COVID-19 disinformation among Blacks in Africa and the African diaspora.MethodsWe searched and reviewed articles from major databases such as MEDLINE, EMBASE, and CINAHL. Our search strategy involved the following concepts: 1) COVID-19, including variants; 2) misinformation, conspiracy theories, and fake news, and modes of misinformation transmission such as social media; and 3) Blacks or people of African descent, or the African diaspora. We retrieved 600 articles that were independently screened by two researchers. We included studies focusing on 1) Black people living inside or outside Africa; and 2) COVID-19 online dis/misinformation among this population. A total of 19 studies fit our inclusion criteria. We used a thematic analysis to analyse qualitative data.ResultsOur findings indicate Black people are accessing and often sharing online disinformation and misinformation primarily through social media platforms such as WhatsApp, Facebook, Twitter, YouTube, and Instagram. Dis/misinformation concerns the origin of COVID-19, transmission, prevention, and treatment of COVID-19, assertions of race immunity to the virus, distrust in government and health organizations, and intervention research and programming.ConclusionsThere is a global paucity of literature addressing COVID-19 online dis/misinformation among Black people. Dis/misinformation can fuel vaccine hesitancy and threaten the goal of herd immunity. Knowledge of the impact and implications of COVID-19 online dis/misinformation is necessary to inform public health interventions in Black communities.
| S-EPMC9304926 | biostudies-literature
Project description:With the exponential growth in the daily publication of scientific articles, automatic classification and categorization can assist in assigning articles to a predefined category. Article titles are concise descriptions of the articles' content with valuable information that can be useful in document classification and categorization. However, shortness, data sparseness, limited word occurrences, and the inadequate contextual information of scientific document titles hinder the direct application of conventional text mining and machine learning algorithms on these short texts, making their classification a challenging task. This study firstly explores the performance of our earlier study, TextNetTopics on the short text. Secondly, here we propose an advanced version called TextNetTopics Pro, which is a novel short-text classification framework that utilizes a promising combination of lexical features organized in topics of words and topic distribution extracted by a topic model to alleviate the data-sparseness problem when classifying short texts. We evaluate our proposed approach using nine state-of-the-art short-text topic models on two publicly available datasets of scientific article titles as short-text documents. The first dataset is related to the Biomedical field, and the other one is related to Computer Science publications. Additionally, we comparatively evaluate the predictive performance of the models generated with and without using the abstracts. Finally, we demonstrate the robustness and effectiveness of the proposed approach in handling the imbalanced data, particularly in the classification of Drug-Induced Liver Injury articles as part of the CAMDA challenge. Taking advantage of the semantic information detected by topic models proved to be a reliable way to improve the overall performance of ML classifiers.
| S-EPMC10585361 | biostudies-literature
Project description:With COVID-19 cases rising rapidly, deep learning has emerged as a promising diagnosis technique. However, identifying the most accurate models to characterize COVID-19 patients is challenging because comparing results obtained with different types of data and acquisition processes is non-trivial. In this paper we designed, evaluated, and compared the performance of 20 convolutional neutral networks in classifying patients as COVID-19 positive, healthy, or suffering from other pulmonary lung infections based on Chest CT scans, serving as the first to consider the EfficientNet family for COVID-19 diagnosis and employ intermediate activation maps for visualizing model performance. All models are trained and evaluated in Python using 4173 Chest CT images from the dataset entitled "A COVID multiclass dataset of CT scans," with 2168, 758, and 1247 images of patients that are COVID-19 positive, healthy, or suffering from other pulmonary infections, respectively. EfficientNet-B5 was identified as the best model with an F1 score of 0.9769±0.0046, accuracy of 0.9759±0.0048, sensitivity of 0.9788±0.0055, specificity of 0.9730±0.0057, and precision of 0.9751± 0.0051. On an alternate 2-class dataset, EfficientNetB5 obtained an accuracy of 0.9845±0.0109, F1 score of 0.9599±0.0251, sensitivity of 0.9682±0.0099, specificity of 0.9883±0.0150, and precision of 0.9526 ± 0.0523. Intermediate activation maps and Gradient-weighted Class Activation Mappings offered human-interpretable evidence of the model's perception of ground-class opacities and consolidations, hinting towards a promising use-case of artificial intelligence-assisted radiology tools. With a prediction speed of under 0.1 seconds on GPUs and 0.5 seconds on CPUs, our proposed model offers a rapid, scalable, and accurate diagnostic for COVID-19.
| S-EPMC8769906 | biostudies-literature
Project description:The COVID-19 pandemic has affected day-to-day activities. Some families experienced a positive impact, such as an increase of bonding between family members. However, there are families that experienced a negative effect, such as the emergence of various conflicts that lead to a divorce. Based on the literature, it can be stated that the COVID-19 pandemic contributed to the increasing number of divorce rates. This paper proposes a convolutional neural network (CNN) classification algorithm in determining the dominant causes of the increase in divorce rate during the COVID-19 pandemic. CNN is considered suitable for classifying large amounts of data. The data used as research materials are available on the official website of the Indonesian Supreme Court. This research utilizes Supreme Court divorce decisions from March 2020 to July 2021, which constitutes 15,997 datasets. The proposed number of layers implemented during the classification is four. The results indicate that the classification using CNN is able to provide an accuracy value of 96% at the 100th epoch. To provide a baseline comparison, the classical support vector machine (SVM) method was performed. The result confirms that CNN outweighs SVM. It is expected that the results will help any parties to provide a suitable anticipation based on the classified dominant causes of the divorce during the COVID-19 pandemic.
| S-EPMC9299239 | biostudies-literature
Project description:Introduction The use of social media during the COVID-19 pandemic has led to an "infodemic" of mis- and disinformation with potentially grave consequences. To explore means of counteracting disinformation, we analyzed tweets containing the hashtags #Scamdemic and #Plandemic. Methods Using a Twitter scraping tool called twint, we collected 419,269 English-language tweets that contained “#Scamdemic” or “#Plandemic” posted in 2020. Using the Twitter application-programming interface, we extracted the same tweets (by tweet ID) with additional user metadata. We explored descriptive statistics of tweets including their content and user profiles, analyzed sentiments and emotions, performed topic modeling, and determined tweet availability in both datasets. Results After removal of retweets, replies, non-English tweets, or duplicate tweets, 40,081 users tweeted 227,067 times using our selected hashtags. The mean weekly sentiment was overall negative for both hashtags. One in five users who used these hashtags were suspended by Twitter by January 2021. Suspended accounts had an average of 610 followers and an average of 6.7 tweets per user, while active users had an average of 472 followers and an average of 5.4 tweets per user. The most frequent tweet topic was “Complaints against mandates introduced during the pandemic” (79,670 tweets), which included complaints against masks, social distancing, and closures. Discussion While social media has democratized speech, it also permits users to disseminate potentially unverified or misleading information that endangers people’s lives and public health interventions. Characterizing tweets and users that use hashtags associated with COVID-19 pandemic denial allowed us to understand the extent of misinformation. With the preponderance of inaccessible original tweets, we concluded that posters were in denial of the COVID-19 pandemic and sought to disperse related mis- or disinformation resulting in suspension. Conclusion Leveraging 227,067 tweets with the hashtags #scamdemic and #plandemic in 2020, we were able to elucidate important trends in public disinformation about the COVID-19 vaccine.
| S-EPMC9216575 | biostudies-literature
Project description:Mice with a human immune system (humanized mice), generated by transplantation of human hematopoietic stem and progenitor cells (HSPCs), serve as invaluable tools to study the development and function of the human immune system in vivo. By adapting recombinant adeno-associated virus (AAV)-driven gene therapy to deliver hACE2 to the lungs, which allows infection with SARS-CoV-2 of MISTRG6 mice engrafted with HPSCs, we created a humanized mouse model of COVID-19 that recapitulates the distribution and function of the human innate and adaptive immune system and is amenable to the mechanistic study of COVID-19 and its myriad of complications. MISTRG6 mouse model was engineered by a human/mouse homolog gene-replacement strategy to provide physiological factors with regard to quantity, location and time and enable essentially all classes of human HSPCs to develop in mice. MISTRG6 (acronym for genes replaced) mice encode humanized M-CSF (enabling monocytes and tissue macrophage development), GM-CSF/IL-3 (to provide lung alveolar macrophages), SIRPa (establish macrophage tolerance to human cells), ThPO (hematopoiesis and platelets), and IL-6 (better engraftment allowing study of adult human patients and improved antigen-specific antibody responses as well as human IL-6 per se), in a Rag2/Gamma common chain deleted background. We evaluated the transcriptional landscape in uninfected and SARS-CoV-2 infected lungs of humanized mice at multiple time points (2, 4, 7, 14, 28 dpi).
2021-11-04 | GSE186794 | GEO
Project description:Single-cell RNA sequencing (scRNA-seq) technology studies transcriptome and cell-to-cell differences from higher single-cell resolution and different perspectives. Despite the advantage of high capture efficiency, downstream functional analysis of scRNA-seq data is made difficult by the excess of zero values (i.e., the dropout phenomenon). To effectively address this problem, we introduced scNTImpute, an imputation framework based on a neural topic model. A neural network encoder is used to extract underlying topic features of single-cell transcriptome data to infer high-quality cell similarity. At the same time, we determine which transcriptome data are affected by the dropout phenomenon according to the learning of the mixture model by the neural network. On the basis of stable cell similarity, the same gene information in other similar cells is borrowed to impute only the missing expression values. By evaluating the performance of real data, scNTImpute can accurately and efficiently identify the dropout values and imputes them accurately. In the meantime, the clustering of cell subsets is improved and the original biological information in cell clustering is solved, which is covered by technical noise. The source code for the scNTImpute module is available as open source at https://github.com/qiyueyang-7/scNTImpute.git.
| S-EPMC10673642 | biostudies-literature