Dataset Information

Labeled entities from social media data related to avian influenza disease.

ABSTRACT: This dataset is composed by spatial (e.g. location) and thematic (e.g. diseases, symptoms, virus) entities concerning avian influenza in social media (textual) data in English. It was created from three corpora: the first one includes 10 transcriptions of YouTube videos and 70 tweets manually annotated. The second corpus is composed by the same textual data but automatically annotated with Named Entity Recognition (NER) tools. These two corpora have been built to evaluate NER tools and apply them to a bigger corpus. The third corpus is composed of 100 YouTube transcriptions automatically annotated with NER tools. The aim of the annotation task is to recognize spatial information such as the names of the cities and epidemiological information such as the names of the diseases. An annotation guideline is provided in order to ensure a unified annotation and to help the annotators. This dataset can be used to train or evaluate Natural Language Processing (NLP) approaches such as specialized entity recognition.

SUBMITTER: Schaeffer C

PROVIDER: S-EPMC9184875 | biostudies-literature | 2022 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Labeled entities from social media data related to avian influenza disease.

Schaeffer Camille C Interdonato Roberto R Lancelot Renaud R Roche Mathieu M Teisseire Maguelonne M

Data in brief 20220527

This dataset is composed by spatial (e.g. location) and thematic (e.g. diseases, symptoms, virus) entities concerning avian influenza in social media (textual) data in English. It was created from three corpora: the first one includes 10 transcriptions of YouTube videos and 70 tweets manually annotated. The second corpus is composed by the same textual data but automatically annotated with Named Entity Recognition (NER) tools. These two corpora have been built to evaluate NER tools and apply the ...[more]

PMID: 35692611

Similar Datasets

Project description:BackgroundAs suggested as early as in 2006, logs of queries submitted to search engines seeking information could be a source for detection of emerging influenza epidemics if changes in the volume of search queries are monitored (infodemiology). However, selecting queries that are most likely to be associated with influenza epidemics is a particular challenge when it comes to generating better predictions.ObjectiveIn this study, we describe a methodological extension for detecting influenza outbreaks using search query data; we provide a new approach for query selection through the exploration of contextual information gleaned from social media data. Additionally, we evaluate whether it is possible to use these queries for monitoring and predicting influenza epidemics in South Korea.MethodsOur study was based on freely available weekly influenza incidence data and query data originating from the search engine on the Korean website Daum between April 3, 2011 and April 5, 2014. To select queries related to influenza epidemics, several approaches were applied: (1) exploring influenza-related words in social media data, (2) identifying the chief concerns related to influenza, and (3) using Web query recommendations. Optimal feature selection by least absolute shrinkage and selection operator (Lasso) and support vector machine for regression (SVR) were used to construct a model predicting influenza epidemics.ResultsIn total, 146 queries related to influenza were generated through our initial query selection approach. A considerable proportion of optimal features for final models were derived from queries with reference to the social media data. The SVR model performed well: the prediction values were highly correlated with the recent observed influenza-like illness (r=.956; P<.001) and virological incidence rate (r=.963; P<.001).ConclusionsThese results demonstrate the feasibility of using search queries to enhance influenza surveillance in South Korea. In addition, an approach for query selection using social media data seems ideal for supporting influenza surveillance based on search query data.

Project description:BackgroundCeliac disease (CD) is a chronic, small intestinal inflammatory disease mediated by dietary gluten and related prolamins. The only current therapeutic option is maintenance of a strict life-long gluten-free diet, which implies substantial burden for CD patients. Different treatment regimes might be feasible, including masking of toxic celiac peptides with blocking antibodies or fragments thereof. The objective of this study was therefore to select and produce a recombinant avian single-chain fragment variable (scFv) directed against peptic-tryptic digested gliadin (PT-Gliadin) and related celiac toxic entities.ResultsGluten-free raised chicken of same age were immunized with PT-Gliadin. Chicken splenic lymphocytes, selected with antigen-coated magnetic beads, served as RNA source for the generation of cDNA. Chicken VH and VL genes were amplified from the cDNA by PCR to generate full-length scFv constructs consisting of VH and VL fragments joined by a linker sequence. ScFv constructs were ligated in a prokaryotic expression vector, which provides a C-terminal hexahistidine tag. ScFvs from several bacterial clones were expressed in soluble form and crude cell lysates screened for binding to PT-Gliadin by ELISA. We identified an enriched scFv motif, which showed reactivity to PT-Gliadin. One selected scFv candidate was expressed and purified to homogeneity. Polyclonal anti-PT-Gliadin IgY, purified from egg yolk of immunized chicken, served as control. ScFv binds in a dose-dependent manner to PT-Gliadin, comparable to IgY. Furthermore, IgY competitively displaces scFv from PT-Gliadin and natural wheat flour digest, indicating a common epitope of scFv and IgY. ScFv was tested for reactivity to different gastric digested dietary grain flours. ScFv detects common and khorasan wheat comparably with binding affinities in the high nanomolar range, while rye is detected to a lesser extent. Notably, barley and cereals which are part of the gluten-free diet, like corn and rice, are not detected by scFv. Similarly, the pseudo-grain amaranth, used as gluten-free alternative, is not targeted by scFv. This data indicate that scFv specifically recognizes toxic cereal peptides relevant in CD.ConclusionScFv can be of benefit for future CD treatment regimes.

Project description:IntroductionWe speculated that social media data from Alzheimer's disease (AD) stakeholders (patients, caregivers, and clinicians) could identify barriers along the patient journey in AD, and that insights gained may help devise strategies to remove barriers, and ultimately improve the patient journey.MethodsOur sample was drawn from a repository of social media posts extracted from 112 public sources between January 1998 and December 2021 using natural language processing text-mining algorithms. The patient journey was classified into three phases: (1) early signs/experiences (Early Signs); (2) screening/assessment/diagnosis (Screening); and (3) treatment/management (Treatment). In the Early Signs phase, issues/challenges derived from a conceptual AD identification framework (ADIF) were examined. In subsequent phases, behavioral/psychiatric challenges, access/barriers to health care, screening/diagnostic methods, and symptomatic treatments for AD were identified. Posts were classified by AD stakeholder type or disease stage, if possible.ResultsWe identified 225,977 AD patient journey-related social media posts. Anxiety was a predominant issue/challenge in all patient journey phases. In the Screening and Treatment phases combined, access/barriers to care were described in 16% of posts; unwillingness/resistance to seeking care was a major barrier (≥ 75% of access-related posts across all stakeholders). Commonly identified structural barriers (e.g., affordability/cost, geography/transportation/distance) were more common in patient/caregiver posts than clinician posts. Among Screening-related posts, imaging/scans were commonly mentioned by all stakeholders; biomarkers were more commonly mentioned by patients than clinicians. Treatment-related concerns were identified in 17% of stakeholder-specified posts that named pharmacological agents/classes for the symptomatic management of AD.ConclusionThis descriptive analysis of out-of-clinic experiences reflected in AD social media posts found that unwillingness/resistance to seeking care was a key barrier, followed by structural barriers to health care, such as affordability/cost. Insights from the lived experiences of AD stakeholders are valuable and highlight the need to improve the patient journey in AD and ease patient and caregiver burden.

Dataset Information

Labeled entities from social media data related to avian influenza disease.

Publications

Labeled entities from social media data related to avian influenza disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets