COVID-19 Open Research Dataset Research Articles

Searching COVID-19 Clinical Research Using Graph Queries: Algorithm Development and Validation.

Since the beginning of the COVID-19 pandemic, >1 million studies have been collected within the COVID-19 Open Research Dataset, a corpus of manuscripts created to accelerate research against the disease. Their related abstracts hold a wealth of information that remains largely unexplored and difficult to search due to its unstructured nature. Keyword-based search is the standard approach, which allows users to retrieve the documents of a corpus that contain (all or some of) the words in a target list. This type of search, however, does not provide visual support to the task and is not suited to expressing complex queries or compensating for missing specifications. This study aims to consider small graphs of concepts and exploit them for expressing graph searches over existing COVID-19-related literature, leveraging the increasing use of graphs to represent and query scientific knowledge and providing a user-friendly search and exploration experience. We considered the COVID-19 Open Research Dataset corpus and summarized its content by annotating the publications' abstracts using terms selected from the Unified Medical Language System and the Ontology of Coronavirus Infectious Disease. Then, we built a co-occurrence network that includes all relevant concepts mentioned in the corpus, establishing connections when their mutual information is relevant. A sophisticated graph query engine was built to allow the identification of the best matches of graph queries on the network. It also supports partial matches and suggests potential query completions using shortest paths. We built a large co-occurrence network, consisting of 128,249 entities and 47,198,965 relationships; the GRAPH-SEARCH interface allows users to explore the network by formulating or adapting graph queries; it produces a bibliography of publications, which are globally ranked; and each publication is further associated with the specific parts of the query that it explains, thereby allowing the user to understand each aspect of the matching. Our approach supports the process of query formulation and evidence search upon a large text corpus; it can be reapplied to any scientific domain where documents corpora and curated ontologies are made available.

Exploring the evolution of research topics during the COVID-19 pandemic

The COVID-19 pandemic has changed the research agendas of most scientific communities, resulting in an overwhelming production of research articles in a variety of domains, including medicine, virology, epidemiology, economy, psychology, and so on. Several open-access corpora and literature hubs were established; among them, the COVID-19 Open Research Dataset (CORD-19) has systematically gathered scientific contributions for 2.5 years, by collecting and indexing over one million articles—this corpus, however, does not provide an easy-to-access overview of its content. Here, we present the CORD-19 Topic Visualizer (CORToViz), a method and associated visualization tool for inspecting the CORD-19 textual corpus of scientific abstracts. Our method is based upon a careful selection of up-to-date technologies (including large language models), resulting in an architecture for clustering articles along orthogonal dimensions and extraction techniques for temporal topic mining. Topic inspection is supported by an interactive dashboard, providing fast, one-click visualization of topic contents as word clouds and topic trends as time series, equipped with easy-to-drive statistical testing for analyzing the significance of topic emergence along arbitrarily selected time windows. Overall, our pipeline is very fast and its results match our expectations on topic identification (F1-score 0.854). The processes of data preparation and results visualization are completely general and virtually applicable to any corpus of textual documents—thus suited for effective adaptation to other contexts.

Machine Learning-Based Approach for Identifying Research Gaps: COVID-19 as a Case Study.

Research gaps refer to unanswered questions in the existing body of knowledge, either due to a lack of studies or inconclusive results. Research gaps are essential starting points and motivation in scientific research. Traditional methods for identifying research gaps, such as literature reviews and expert opinions, can be time consuming, labor intensive, and prone to bias. They may also fall short when dealing with rapidly evolving or time-sensitive subjects. Thus, innovative scalable approaches are needed to identify research gaps, systematically assess the literature, and prioritize areas for further study in the topic of interest. In this paper, we propose a machine learning-based approach for identifying research gaps through the analysis of scientific literature. We used the COVID-19 pandemic as a case study. We conducted an analysis to identify research gaps in COVID-19 literature using the COVID-19 Open Research (CORD-19) data set, which comprises 1,121,433 papers related to the COVID-19 pandemic. Our approach is based on the BERTopic topic modeling technique, which leverages transformers and class-based term frequency-inverse document frequency to create dense clusters allowing for easily interpretable topics. Our BERTopic-based approach involves 3 stages: embedding documents, clustering documents (dimension reduction and clustering), and representing topics (generating candidates and maximizing candidate relevance). After applying the study selection criteria, we included 33,206 abstracts in the analysis of this study. The final list of research gaps identified 21 different areas, which were grouped into 6 principal topics. These topics were: "virus of COVID-19," "risk factors of COVID-19," "prevention of COVID-19," "treatment of COVID-19," "health care delivery during COVID-19," "and impact of COVID-19." The most prominent topic, observed in over half of the analyzed studies, was "the impact of COVID-19." The proposed machine learning-based approach has the potential to identify research gaps in scientific literature. This study is not intended to replace individual literature research within a selected topic. Instead, it can serve as a guide to formulate precise literature search queries in specific areas associated with research questions that previous publications have earmarked for future exploration. Future research should leverage an up-to-date list of studies that are retrieved from the most common databases in the target area. When feasible, full texts or, at minimum, discussion sections should be analyzed rather than limiting their analysis to abstracts. Furthermore, future studies could evaluate more efficient modeling algorithms, especially those combining topic modeling with statistical uncertainty quantification, such as conformal prediction.

Denominative variation in the COVID-19 Open Research Dataset corpus

Abstract Since 2020, we have witnessed the emergence of new concepts and terms due to the pandemic outbreak. Some of them have even become obsolete in a short period of time whereas others are still misused despite standardization efforts. In this paper we study explicit denominative variation in the COVID-19 corpus, which consists of scientific articles released as part of the COVID-19 Open Research Dataset and is publicly available in Sketch Engine. First of all, variants for severe acute respiratory syndrome coronavirus 2 and coronavirus disease 2019 were extracted by means of knowledge patterns (e.g., also known as). The productiveness of knowledge patterns was analyzed and a set of 1,684 explicit variation excerpts were collected and manually annotated. A total of 371 variants were retrieved and organized in two polydenominative clusters (i.e., 177 for COVID-19 and 193 for SARS-CoV-2), which were then formally and semantically characterized by comparison with the established designations. Finally, possible causes underlying denominative variation are explored.

Large-Scale Knowledge Synthesis and Complex Information Retrieval from Biomedical Documents

Recent advances in the healthcare industry have led to an abundance of unstructured data, making it challenging to perform tasks such as efficient and accurate information retrieval at scale. Our work offers an all-in-one scalable solution for extracting and exploring complex information from large-scale research documents, which would otherwise be tedious. First, we briefly explain our knowledge synthesis process to extract helpful information from unstructured text data of research documents. Then, on top of the knowledge extracted from the documents, we perform complex information retrieval using three major components- Paragraph Retrieval, Triplet Retrieval from Knowledge Graphs, and Complex Question Answering (QA). These components combine lexical and semantic-based methods to retrieve paragraphs and triplets and perform faceted refinement for filtering these search results. The complexity of biomedical queries and documents necessitates using a QA system capable of handling queries more complex than factoid queries, which we evaluate qualitatively on the COVID-19 Open Research Dataset (CORD-19) to demonstrate the effectiveness and valueadd.

Construction and evaluation of a domain-specific knowledge graph for knowledge discovery

PurposeThis study aims to evaluate a method of building a biomedical knowledge graph (KG).Design/methodology/approachThis research first constructs a COVID-19 KG on the COVID-19 Open Research Data Set, covering information over six categories (i.e. disease, drug, gene, species, therapy and symptom). The construction used open-source tools to extract entities, relations and triples. Then, the COVID-19 KG is evaluated on three data-quality dimensions: correctness, relatedness and comprehensiveness, using a semiautomatic approach. Finally, this study assesses the application of the KG by building a question answering (Q&A) system. Five queries regarding COVID-19 genomes, symptoms, transmissions and therapeutics were submitted to the system and the results were analyzed.FindingsWith current extraction tools, the quality of the KG is moderate and difficult to improve, unless more efforts are made to improve the tools for entity extraction, relation extraction and others. This study finds that comprehensiveness and relatedness positively correlate with the data size. Furthermore, the results indicate the performances of the Q&A systems built on the larger-scale KGs are better than the smaller ones for most queries, proving the importance of relatedness and comprehensiveness to ensure the usefulness of the KG.Originality/valueThe KG construction process, data-quality-based and application-based evaluations discussed in this paper provide valuable references for KG researchers and practitioners to build high-quality domain-specific knowledge discovery systems.

Predictors of intrahospital mortality in patients with coronavirus disease 2019 and cerebrovascular diseases: rapid systematic review and meta-analysis protocol

Background: Coronavirus disease 2019 (COVID19) is a novel pandemic disease caused by the β-coronavirus SARS-CoV-2. This disease affects primarily the respiratory organs, but the vascular system may also be compromised. COVID19 may lead to either coagulopathies or hemorrhagic disorders involving the central nervous system. Risk factors for a fatal outcome have been suggested but not completely elucidated. Objectives: This systematic review protocol aims to identify clinical, imaging and laboratory variables associated with intra-hospital mortality in patients with COVID19 and cerebrovascular disease. Materials and Methods: Studies will be retrieved from Web of Science, MEDLINE, Scopus, EBSCOhost, Ovid, Rayyan’s COVID-19 Open Research Dataset, and Google Scholar. Inclusion criteria will be observational studies or clinical trials describing patients with both COVID19 and cerebrovascular disease. Exclusion criteria will be studies whose patients remained hospitalized with no defined outcome (intrahospital mortality or discharge), studies written in languages different than English, published before 2019 or whose full-texts could not be retrieved. All demographic, laboratory and imaging variables will be extracted. Data synthesis will be presented in graphs, figures, and summary of findings tables. A global mortality rate will be calculated. A narrative synthesis will be included. A meta-analysis will be performed. For mortality rate and statistical synthesis, only studies reporting the main outcome (intra-hospital mortality or discharge) will be considered. Quality of the evidence will be assessed with the JBI Critical Appraisal tools. This protocol received no funding and isregistered in PROSPERO.

Predictors of intrahospital mortality in patients with coronavirus disease 2019 and cerebrovascular diseases: rapid systematic review and meta-analysis protocol

Background: Coronavirus disease 2019 (COVID19) is a novel pandemic disease caused by the β-coronavirus SARS-CoV-2. This disease affects primarily the respiratory organs, but the vascular system may also be compromised. COVID19 may lead to either coagulopathies or hemorrhagic disorders involving the central nervous system. Risk factors for a fatal outcome have been suggested but not completely elucidated. Objectives: This systematic review protocol aims to identify clinical, imaging and laboratory variables associated with intra-hospital mortality in patients with COVID19 and cerebrovascular disease. Materials and Methods: Studies will be retrieved from Web of Science, MEDLINE, Scopus, EBSCOhost, Ovid, Rayyan’s COVID-19 Open Research Dataset, and Google Scholar. Inclusion criteria will be observational studies or clinical trials describing patients with both COVID19 and cerebrovascular disease. Exclusion criteria will be studies whose patients remained hospitalized with no defined outcome (intrahospital mortality or discharge), studies written in languages different than English, published before 2019 or whose full-texts could not be retrieved. All demographic, laboratory and imaging variables will be extracted. Data synthesis will be presented in graphs, figures, and summary of findings tables. A global mortality rate will be calculated. A narrative synthesis will be included. A meta-analysis will be performed. For mortality rate and statistical synthesis, only studies reporting the main outcome (intra-hospital mortality or discharge) will be considered. Quality of the evidence will be assessed with the JBI Critical Appraisal tools. This protocol received no funding and isregistered in PROSPERO.

Deep representation learning of scientific paper reveals its potential scholarly impact

Citation and citation-based metrics are traditionally used to quantify the scholarly impact of scientific papers. However, for documents without citation data, i.e., newly published papers, the citation-based metrics are not available. By leveraging deep representation techniques, we propose a text-content based approach that may reveal the scholarly impact of papers without human domain-specific knowledge. Specifically, a large-scale Pre-Trained Model (PTM) with 110 million parameters is utilized to automatically encode the paper into the vector representation. Two indicators, τ (Topicality) and σ (Originality), are then proposed based on the learned representations. These two indicators leverage the spatial relations of paper representations in the semantic space to capture the impact-related characteristics of a scientific paper. Extensive experiments have been conducted on a COVID-19 open research dataset with 1,056,660 papers. The experimental results demonstrate that the deep representation learning method can better capture the scientific content in the published literature; and the proposed indicators are positively and significantly associated with a paper’s potential scholarly impact. In the multivariate regression analysis for the potential impact of a paper, the coefficients of σ and τ are 5.4915 (P<0.001) and 6.6879 (P<0.001) for next 6 months prediction, 12.9964 (P<0.001) and 13.8678 (P<0.001) for next 12 months prediction. The proposed framework may facilitate the study of how scholarly impact is generated, from a textual representation perspective.

Using active learning and an agent-based system to perform interactive knowledge extraction based on the COVID-19 corpus

Abstract Efficient knowledge extraction from Big Data is quite a challenging topic. Recognizing relevant concepts from unannotated data while considering both context and domain knowledge is critical to implementing successful knowledge extraction. In this research, we provide a novel platform we call Active Learning Integrated with Knowledge Extraction (ALIKE) that overcomes the challenges of context awareness and concept extraction, which have impeded knowledge extraction in Big Data. We propose a method to extract related concepts from unorganized data with different contexts using multiple agents, synergy, reinforcement learning, and active learning. We test ALIKE on the datasets of the COVID-19 Open Research Dataset Challenge. The experiment result suggests that the ALIKE platform can more efficiently distinguish inherent concepts from different papers than a non-agent-based method (without active learning) and that our proposed approach has a better chance to address the challenges of knowledge extraction with heterogeneous datasets. Moreover, the techniques used in ALIKE are transferable across any domain with multidisciplinary activity.

Dynamic Link Prediction for Discovery of New Impactful COVID-19 Research Approaches.

In fighting the COVID-19 pandemic, the main challenges include the lack of prior research and the urgency to find effective solutions. It is essential to accurately and rapidly summarize the relevant research work and explore potential solutions for diagnosis, treatment and prevention of COVID-19. It is a daunting task to summarize the numerous existing research works and to assess their effectiveness. This paper explores the discovery of new COVID-19 research approaches based on dynamic link prediction, which analyze the dynamic topological network of keywords to predict possible connections of research concepts. A dynamic link prediction method based on multi-granularity feature fusion is proposed. Firstly, a multi-granularity temporal feature fusion method is adopted to extract the temporal evolution of different order subgraphs. Secondly, a hierarchical feature weighting method is proposed to emphasize actively evolving nodes. Thirdly, a semantic repetition sampling mechanism is designed to avoid the negative effect of semantically equivalent medical entities on the real structure of the graph, and to capture the real topological structure features. Experiments are performed on the COVID-19 Open Research Dataset to assess the performance of the model. The results show that the proposed model performs significantly better than existing state-of-the-art models, thereby confirming the effectiveness of the proposed method for the discovery of new COVID-19 research approaches.

Knowledge4COVID-19: A semantic-based approach for constructing a COVID-19 related knowledge graph from various sources and analyzing treatments’ toxicities

In this paper, we present Knowledge4COVID-19, a framework that aims to showcase the power of integrating disparate sources of knowledge to discover adverse drug effects caused by drug–drug interactions among COVID-19 treatments and pre-existing condition drugs. Initially, we focus on constructing the Knowledge4COVID-19 knowledge graph (KG) from the declarative definition of mapping rules using the RDF Mapping Language. Since valuable information about drug treatments, drug–drug interactions, and side effects is present in textual descriptions in scientific databases (e.g., DrugBank) or in scientific literature (e.g., the CORD-19, the Covid-19 Open Research Dataset), the Knowledge4COVID-19 framework implements Natural Language Processing. The Knowledge4COVID-19 framework extracts relevant entities and predicates that enable the fine-grained description of COVID-19 treatments and the potential adverse events that may occur when these treatments are combined with treatments of common comorbidities, e.g., hypertension, diabetes, or asthma. Moreover, on top of the KG, several techniques for the discovery and prediction of interactions and potential adverse effects of drugs have been developed with the aim of suggesting more accurate treatments for treating the virus. We provide services to traverse the KG and visualize the effects that a group of drugs may have on a treatment outcome. Knowledge4COVID-19 was part of the Pan-European hackathon#EUvsVirus in April 2020 and is publicly available as a resource through a GitHub repository and a DOI.

The impact of the COVID-19 pandemic on presentations to health services following self-harm: systematic review.

Evidence on the impact of the pandemic on healthcare presentations for self-harm has accumulated rapidly. However, existing reviews do not include studies published beyond 2020. To systematically review evidence on presentations to health services following self-harm during the COVID-19 pandemic. A comprehensive search of databases (WHO COVID-19 database; Medline; medRxiv; Scopus; PsyRxiv; SocArXiv; bioRxiv; COVID-19 Open Research Dataset, PubMed) was conducted. Studies published from 1 January 2020 to 7 September 2021 were included. Study quality was assessed with a critical appraisal tool. Fifty-one studies were included: 57% (29/51) were rated as 'low' quality, 31% (16/51) as 'moderate' and 12% (6/51) as 'high-moderate'. Most evidence (84%, 43/51) was from high-income countries. A total of 47% (24/51) of studies reported reductions in presentation frequency, including all six rated as high-moderate quality, which reported reductions of 17-56%. Settings treating higher lethality self-harm were overrepresented among studies reporting increased demand. Two of the three higher-quality studies including study observation months from 2021 reported reductions in self-harm presentations. Evidence from 2021 suggests increased numbers of presentations among adolescents, particularly girls. Sustained reductions in numbers of self-harm presentations were seen into the first half of 2021, although this evidence is based on a relatively small number of higher-quality studies. Evidence from low- and middle-income countries is lacking. Increased numbers of presentations among adolescents, particularly girls, into 2021 is concerning. Findings may reflect changes in thresholds for help-seeking, use of alternative sources of support and variable effects of the pandemic across groups.

UGDAS: Unsupervised graph-network based denoiser for abstractive summarization in biomedical domain.

Abstractive summarization models can generate summary auto-regressively, but the quality is often impacted by the noise in the text. Learning cross-sentence relations is a crucial step in this task and the graph-based network is more effective to capture the sentence relationship. Moreover, knowledge is very important to distinguish the noise of the text in special domain. A novel model structure called UGDAS is proposed in this paper, which combines a sentence-level denoiser based on an unsupervised graph-network and an auto-regressive generator. It utilizes domain knowledge and sentence position information to denoise the original text and further improve the quality of generated summaries. We use the recently-introduced dataset CORD-19 (COVID-19 Open Research Dataset) on text summarization task, which contains large-scale data on coronaviruses. The experimental results show that our model achieves the SOTA (state-of-the-art) result on CORD-19 dataset and outperforms the related baseline models on the PubMed Abstract dataset.

Accelerating COVID-19 Research with Graph Mining and Transformer-Based Learning

In 2020, the White House released the “Call to Action to the Tech Community on New Machine Readable COVID-19 Dataset,” wherein artificial intelligence experts are asked to collect data and develop text mining techniques that can help the science community answer high-priority scientific questions related to COVID-19. The Allen Institute for AI and collaborators announced the availability of a rapidly growing open dataset of publications, the COVID-19 Open Research Dataset (CORD-19). As the pace of research accelerates, biomedical scientists struggle to stay current. To expedite their investigations, scientists leverage hypothesis generation systems, which can automatically inspect published papers to discover novel implicit connections. We present automated general purpose hypothesis generation systems AGATHA-C and AGATHA-GP for COVID-19 research. The systems are based on the graph mining and transformer models. The systems are massively validated using retrospective information rediscovery and proactive analysis involving human-in-the-loop expert analysis. Both systems achieve high-quality predictions across domains in fast computational time and are released to the broad scientific community to accelerate biomedical research. In addition, by performing the domain expert curated study, we show that the systems are able to discover ongoing research findings such as the relationship between COVID-19 and oxytocin hormone. All code, details, and pre-trained models are available at https://github.com/IlyaTyagin/AGATHA-C-GP.

Suicide and self-harm in low- and middle- income countries during the COVID-19 pandemic: A systematic review.

There is widespread concern over the potential impact of the COVID-19 pandemic on suicide and self-harm globally, particularly in low- and middle-income countries (LMIC) where the burden of these behaviours is greatest. We synthesised the evidence from the published literature on the impact of the pandemic on suicide and self-harm in LMIC. This review is nested within a living systematic review (PROSPERO ID CRD42020183326) that continuously identifies published evidence (all languages) through a comprehensive automated search of multiple databases (PubMed; Scopus; medRxiv, PsyArXiv; SocArXiv; bioRxiv; the WHO COVID-19 database; and the COVID-19 Open Research Dataset by Semantic Scholar (up to 11/2020), including data from Microsoft Academic, Elsevier, arXiv and PubMed Central.) All articles identified by the 4th August 2021 were screened. Papers reporting on data from a LMIC and presenting evidence on the impact of the pandemic on suicide or self-harm were included. Methodological quality was assessed using an appropriate tool, and a narrative synthesis presented. A total of 22 studies from LMIC were identified representing data from 12 countries. There was an absence of data from Africa, the Pacific, and the Caribbean. The reviewed studies mostly report on the early months of COVID-19 and were generally methodologically poor. Few studies directly assessed the impact of the pandemic. The most robust evidence, from time-series studies, indicate either a reduction or no change in suicide and self-harm behaviour. As LMIC continue to experience repeated waves of the virus and increased associated mortality, against a backdrop of vaccine inaccessibility and limited welfare support, continued efforts are needed to track the indirect impact of the pandemic on suicide and self-harm in these countries.

Efficacy of covid-19 vaccines in immunocompromised patients: systematic review and meta-analysis.

ObjectiveTo compare the efficacy of covid-19 vaccines between immunocompromised and immunocompetent people.DesignSystematic review and meta-analysis.Data sourcesPubMed, Embase, Central Register of Controlled Trials, COVID-19 Open Research Dataset Challenge (CORD-19), and WHO covid-19 databases for studies published between 1 December 2020 and 5 November 2021. ClinicalTrials.gov and the WHO International Clinical Trials Registry Platform were searched in November 2021 to identify registered but as yet unpublished or ongoing studies.Study selectionProspective observational studies comparing the efficacy of covid-19 vaccination in immunocompromised and immunocompetent participants.MethodsA frequentist random effects meta-analysis was used to separately pool relative and absolute risks of seroconversion after the first and second doses of a covid-19 vaccine. Systematic review without meta-analysis of SARS-CoV-2 antibody titre levels was performed after first, second, and third vaccine doses and the seroconversion rate after a third dose. Risk of bias and certainty of evidence were assessed.Results82 studies were included in the meta-analysis. Of these studies, 77 (94%) used mRNA vaccines, 16 (20%) viral vector vaccines, and 4 (5%) inactivated whole virus vaccines. 63 studies were assessed to be at low risk of bias and 19 at moderate risk of bias. After one vaccine dose, seroconversion was about half as likely in patients with haematological cancers (risk ratio 0.40, 95% confidence interval 0.32 to 0.50, I2=80%; absolute risk 0.29, 95% confidence interval 0.20 to 0.40, I2=89%), immune mediated inflammatory disorders (0.53, 0.39 to 0.71, I2=89%; 0.29, 0.11 to 0.58, I2=97%), and solid cancers (0.55, 0.46 to 0.65, I2=78%; 0.44, 0.36 to 0.53, I2=84%) compared with immunocompetent controls, whereas organ transplant recipients were 16 times less likely to seroconvert (0.06, 0.04 to 0.09, I2=0%; 0.06, 0.04 to 0.08, I2=0%). After a second dose, seroconversion remained least likely in transplant recipients (0.39, 0.32 to 0.46, I2=92%; 0.35, 0.26 to 0.46), with only a third achieving seroconversion. Seroconversion was increasingly likely in patients with haematological cancers (0.63, 0.57 to 0.69, I2=88%; 0.62, 0.54 to 0.70, I2=90%), immune mediated inflammatory disorders (0.75, 0.69 to 0.82, I2=92%; 0.77, 0.66 to 0.85, I2=93%), and solid cancers (0.90, 0.88 to 0.93, I2=51%; 0.89, 0.86 to 0.91, I2=49%). Seroconversion was similar between people with HIV and immunocompetent controls (1.00, 0.98 to 1.01, I2=0%; 0.97, 0.83 to 1.00, I2=89%). Systematic review of 11 studies showed that a third dose of a covid-19 mRNA vaccine was associated with seroconversion among vaccine non-responders with solid cancers, haematological cancers, and immune mediated inflammatory disorders, although response was variable in transplant recipients and inadequately studied in people with HIV and those receiving non-mRNA vaccines.ConclusionSeroconversion rates after covid-19 vaccination were significantly lower in immunocompromised patients, especially organ transplant recipients. A second dose was associated with consistently improved seroconversion across all patient groups, albeit at a lower magnitude for organ transplant recipients. Targeted interventions for immunocompromised patients, including a third (booster) dose, should be performed.Systematic review registrationPROSPERO CRD42021272088.

COVIDSum: A linguistically enriched SciBERT-based summarization model for COVID-19 scientific papers

The coronavirus disease (COVID-19) has claimed the lives of over 350,000 people and infected more than 173 million people worldwide, it triggers researchers from diverse fields are accelerating their research to help diagnostics, therapies, and vaccines. Researchers also publish their recent research progress through scientific papers. However, manually writing the abstract of a paper is time-consuming, and it increases the writing burden of the researchers. Abstractive summarization technique which automatically provides researchers reliable draft abstracts, can alleviate this problem. In this work, we propose a linguistically enriched SciBERT-based summarization model for COVID-19 scientific papers, named COVIDSum. Specifically, we first extract salient sentences from source papers and construct word co-occurrence graphs. Then, we adopt a SciBERT-based sequence encoder and a Graph Attention Networks-based graph encoder to encode sentences and word co-occurrence graphs, respectively. Finally, we fuse the above two encodings and generate an abstractive summary of each scientific paper. When evaluated on the publicly available COVID-19 open research dataset, the performance of our proposed model achieves significant improvement compared with other document summarization models.

A topic trend analysis on COVID-19 literature.

In the past 2 years, the number of scientific publications has grown exponentially. The COVID-19 outbreak hugely contributed to this dramatic increase in the volume of published research. Currently, text mining of the volume of SARS-CoV-2 and COVID-19 publications is limited to the first months of the outbreak. We aim to identify the major topics in COVID-19 literature collected from several citational sources and analyze the temporal trend from November 2019 to December 2021. We performed an extensive literature search on SARS-Cov-2 and COVID-19 publications on PubMed, Scopus, and Web of Science (WoS) and a structural topic modelling on the retrieved abstracts. The temporal trend of the recognized topics was analyzed. Furthermore, a comparison between our corpus and the COVID-19 Open Research Dataset (CORD-19) repository was performed. We collected 269,186 publications and identified 10 topics. The most popular topic was related to the clinical pictures of the COVID-19 outbreak, which has a constant trend, and the least popular includes studies on COVID-19 literature and databases. "Telemedicine", "Vaccine development", and "Epidemiology" were popular topics in the early phase of the pandemic; increasing topics in the last period are "COVID-19 impact on mental health", "Forecasting", and "Molecular Biology". "Education" was the second most popular topic, which emerged in September 2020. We identified 10 topics for classifying COVID-19 research publications and estimated a nonlinear temporal trend that gives an overview of their unfolding over time. Several citational databases must be searched to retrieve a complete set of studies despite the efforts to build repositories for COVID-19 literature. Our collected data can help build a more focused literature search between November 2019 and December 2021 when carrying out systematic and rapid reviews and our findings can give a complete picture on the topic.

Sparse Topic Modeling: Computational Efficiency, Near-Optimal Algorithms, and Statistical Inference

Sparse topic modeling under the probabilistic latent semantic indexing (pLSI) model is studied. Novel and computationally fast algorithms for estimation and inference of both the word-topic matrix and the topic-document matrix are proposed and their theoretical properties are investigated. Both minimax upper and lower bounds are established and the results show that the proposed algorithms are rate-optimal, up to a logarithmic factor. Moreover, a refitting algorithm is proposed to establish asymptotic normality and construct valid confidence intervals for the individual entries of the word-topic and topic-document matrices. Simulation studies are carried out to investigate the numerical performance of the proposed algorithms. The results show that the proposed algorithms perform well numerically and are more accurate in a range of simulation settings comparing to the existing literature. In addition, the methods are illustrated through an analysis of the COVID-19 Open Research Dataset (CORD-19).