A corpus for mining drug-related knowledge from Twitter chatter: Language models and their utilities.
Ontology highlight
ABSTRACT:
SUBMITTER: Sarker A
PROVIDER: S-EPMC5144647 | biostudies-literature | 2017 Feb
REPOSITORIES: biostudies-literature
Publications
A corpus for mining drug-related knowledge from Twitter chatter: Language models and their utilities.
Sarker Abeed A Gonzalez Graciela G
Data in brief 20161123
In this data article, we present to the data science, natural language processing and public heath communities an unlabeled corpus and a set of language models. We collected the data from Twitter using drug names as keywords, including their common misspelled forms. Using this data, which is rich in drug-related chatter, we developed language models to aid the development of data mining tools and methods in this domain. We generated several models that capture (i) distributed word representation ...[more]
Similar Datasets
Project description:When the Zika virus outbreak became a global health emergency in early 2016, the scientific community responded with an increased output of Zika-related research. This upsurge in research naturally made its way into academic journals along with editorials, news, and reports. However, it is not yet known how or whether these scholarly communications were distributed to the populations most affected by Zika.To understand how scientific outputs about Zika reached global and local audiences, we collected Tweets and Facebook posts that linked to Zika-related research in the first six months of 2016. Using a language detection algorithm, we found that up to 90% of Twitter and 76% of Facebook posts are in English. However, when none of the authors of the scholarly article are from English-speaking countries, posts on both social media are less likely to be in English. The effect is most pronounced on Facebook, where the likelihood of posting in English is between 11 and 16% lower when none of the authors are from English-speaking countries, as compared to when some or all are. Similarly, posts about papers written with a Brazilian author are 13% more likely to be in Portuguese on Facebook than when made on Twitter.Our main conclusion is that scholarly communication on Twitter and Facebook of Zika-related research is dominated by English, despite Brazil being the epicenter of the Zika epidemic. This result suggests that scholarly findings about the Zika virus are unlikely to be distributed directly to relevant populations through these popular online mediums. Nevertheless, there are differences between platforms. Compared to Twitter, scholarly communication on Facebook is more likely to be in the language of an author's country. The Zika outbreak provides a useful case-study for understanding how scientific outputs are communicated to relevant populations. Our results suggest that Facebook is a more effective channel than Twitter, if communication is desired to be in the native language of the affected country. Further research should explore how local media-such as governmental websites, newspapers and magazines, as well as television and radio-disseminate scholarly publication.
| S-EPMC5755770 | biostudies-literature
Project description:With roots as a public health campaign in the United Kingdom, "Dry January" is a temporary alcohol abstinence initiative encouraging participants to abstain from alcohol use during the month of January. Dry January has become a cultural phenomenon, gaining increasing news media attention and social media engagement. Given the utility of capturing naturalistic discussions around health topics on social media, we examined Twitter chatter about Dry January and associated temporary abstinence experiences. Public tweets were collected containing the search terms "dry january" or "dryjanuary" posted between 15 December and 15 February across 3 years (2020-2). A random subsample stratified by year (n = 3145) was pulled for manual content analysis by trained coders. Final codebook accounted for user sentiment toward Dry January, user account type, and themes related to Dry January participation. Engagement metadata (e.g. likes) were also collected. Though user sentiment was mixed, most tweets expressed positive or neutral sentiment toward Dry January (74.7%). Common themes included encouragement and support for Dry January participation (14.1%), experimentation with and promotion of nonalcoholic drinks (14.0%), and benefits derived from Dry January participation (10.4%). While there is promise in the movement to promote positive alcohol-related behavior change, increased efforts to deliver the campaign within a public health context are needed. Health communication campaigns designed to inform participants about evidence-based treatment and recovery support services proven to help people quit or cut down on their drinking are likely to maximize benefits.
| S-EPMC10642608 | biostudies-literature
Project description:BackgroundTo date, there are no effective treatments for most neurodegenerative diseases. Knowledge graphs can provide comprehensive and semantic representation for heterogeneous data, and have been successfully leveraged in many biomedical applications including drug repurposing. Our objective is to construct a knowledge graph from literature to study the relations between Alzheimer's disease (AD) and chemicals, drugs and dietary supplements in order to identify opportunities to prevent or delay neurodegenerative progression. We collected biomedical annotations and extracted their relations using SemRep via SemMedDB. We used both a BERT-based classifier and rule-based methods during data preprocessing to exclude noise while preserving most AD-related semantic triples. The 1,672,110 filtered triples were used to train with knowledge graph completion algorithms (i.e., TransE, DistMult, and ComplEx) to predict candidates that might be helpful for AD treatment or prevention.ResultsAmong three knowledge graph completion models, TransE outperformed the other two (MR = 10.53, Hits@1 = 0.28). We leveraged the time-slicing technique to further evaluate the prediction results. We found supporting evidence for most highly ranked candidates predicted by our model which indicates that our approach can inform reliable new knowledge.ConclusionThis paper shows that our graph mining model can predict reliable new relationships between AD and other entities (i.e., dietary supplements, chemicals, and drugs). The knowledge graph constructed can facilitate data-driven knowledge discoveries and the generation of novel hypotheses.
| S-EPMC9523633 | biostudies-literature
Project description:BackgroundThe growing recognition of the microbiome's impact on human health and well-being has prompted extensive research into discovering the links between microbiome dysbiosis and disease (healthy) states. However, this valuable information is scattered in unstructured form within biomedical literature. The structured extraction and qualification of microbe-disease interactions are important. In parallel, recent advancements in deep-learning-based natural language processing algorithms have revolutionized language-related tasks such as ours. This study aims to leverage state-of-the-art deep-learning language models to extract microbe-disease relationships from biomedical literature.ResultsIn this study, we first evaluate multiple pre-trained large language models within a zero-shot or few-shot learning context. In this setting, the models performed poorly out of the box, emphasizing the need for domain-specific fine-tuning of these language models. Subsequently, we fine-tune multiple language models (specifically, GPT-3, BioGPT, BioMedLM, BERT, BioMegatron, PubMedBERT, BioClinicalBERT, and BioLinkBERT) using labeled training data and evaluate their performance. Our experimental results demonstrate the state-of-the-art performance of these fine-tuned models ( specifically GPT-3, BioMedLM, and BioLinkBERT), achieving an average F1 score, precision, and recall of over [Formula: see text] compared to the previous best of 0.74.ConclusionOverall, this study establishes that pre-trained language models excel as transfer learners when fine-tuned with domain and problem-specific data, enabling them to achieve state-of-the-art results even with limited training data for extracting microbiome-disease interactions from scientific publications.
| S-EPMC10357883 | biostudies-literature
Project description:ImportanceAutomatic curation of consumer-generated, opioid-related social media big data may enable real-time monitoring of the opioid epidemic in the United States.ObjectiveTo develop and validate an automatic text-processing pipeline for geospatial and temporal analysis of opioid-mentioning social media chatter.Design, setting, and participantsThis cross-sectional, population-based study was conducted from December 1, 2017, to August 31, 2019, and used more than 3 years of publicly available social media posts on Twitter, dated from January 1, 2012, to October 31, 2015, that were geolocated in Pennsylvania. Opioid-mentioning tweets were extracted using prescription and illicit opioid names, including street names and misspellings. Social media posts (tweets) (n = 9006) were manually categorized into 4 classes, and training and evaluation of several machine learning algorithms were performed. Temporal and geospatial patterns were analyzed with the best-performing classifier on unlabeled data.Main outcomes and measuresPearson and Spearman correlations of county- and substate-level abuse-indicating tweet rates with opioid overdose death rates from the Centers for Disease Control and Prevention WONDER database and with 4 metrics from the National Survey on Drug Use and Health for 3 years were calculated. Classifier performances were measured through microaveraged F1 scores (harmonic mean of precision and recall) or accuracies and 95% CIs.ResultsA total of 9006 social media posts were annotated, of which 1748 (19.4%) were related to abuse, 2001 (22.2%) were related to information, 4830 (53.6%) were unrelated, and 427 (4.7%) were not in the English language. Yearly rates of abuse-indicating social media post showed statistically significant correlation with county-level opioid-related overdose death rates (n = 75) for 3 years (Pearson r = 0.451, P < .001; Spearman r = 0.331, P = .004). Abuse-indicating tweet rates showed consistent correlations with 4 NSDUH metrics (n = 13) associated with nonmedical prescription opioid use (Pearson r = 0.683, P = .01; Spearman r = 0.346, P = .25), illicit drug use (Pearson r = 0.850, P < .001; Spearman r = 0.341, P = .25), illicit drug dependence (Pearson r = 0.937, P < .001; Spearman r = 0.495, P = .09), and illicit drug dependence or abuse (Pearson r = 0.935, P < .001; Spearman r = 0.401, P = .17) over the same 3-year period, although the tests lacked power to demonstrate statistical significance. A classification approach involving an ensemble of classifiers produced the best performance in accuracy or microaveraged F1 score (0.726; 95% CI, 0.708-0.743).Conclusions and relevanceThe correlations obtained in this study suggest that a social media-based approach reliant on supervised machine learning may be suitable for geolocation-centric monitoring of the US opioid epidemic in near real time.
| S-EPMC6865282 | biostudies-literature
Project description:As the COVID-19 pandemic continues to spread worldwide, an unprecedented amount of open data is being generated for medical, genetics, and epidemiological research. The unparalleled rate at which many research groups around the world are releasing data and publications on the ongoing pandemic is allowing other scientists to learn from local experiences and data generated on the front lines of the COVID-19 pandemic. However, there is a need to integrate additional data sources that map and measure the role of social dynamics of such a unique worldwide event in biomedical, biological, and epidemiological analyses. For this purpose, we present a large-scale curated dataset of over 1.12 billion tweets, growing daily, related to COVID-19 chatter generated from 1 January 2020 to 27 June 2021 at the time of writing. This data source provides a freely available additional data source for researchers worldwide to conduct a wide and diverse number of research projects, such as epidemiological analyses, emotional and mental responses to social distancing measures, the identification of sources of misinformation, stratified measurement of sentiment towards the pandemic in near real time, among many others.
| S-EPMC9620940 | biostudies-literature
Project description:Te reo Māori, the Indigenous language of Aotearoa New Zealand, is a distinctive feature of the nation's cultural heritage. This paper documents our efforts to build a corpus of 79,000 Māori-language tweets using computational methods. The Reo Māori Twitter (RMT) Corpus was created by targeting Māori-language users identified by the Indigenous Tweets website, pre-processing their data and filtering out non-Māori tweets, together with other sources of noise. Our motivation for creating such a resource is three-fold: (1) it serves as a rich and unique dataset for linguistic analysis of te reo Māori on social media; (2) it can be used as training data to develop and augment Natural Language Processing (NLP) tools with robust, real-world Māori-language applications; and (3) it will potentially promote awareness of, and encourage positive interaction with, the growing community of Māori tweeters, thereby increasing the use and visibility of te reo Māori in an online environment. While the corpus captures data from 2007 to 2020, our analysis shows that the number of tweets in the RMT Corpus peaked in 2014, and the number of active tweeters peaked in 2017, although at least 600 users were still active in 2020. To the best of our knowledge, the RMT Corpus is the largest publicly-available collection of social media data containing (almost) exclusively Māori text, making it a useful resource for language experts, NLP developers and Indigenous researchers alike.Supplementary informationThe online version contains supplementary material available at 10.1007/s10579-022-09580-w.
| S-EPMC8852919 | biostudies-literature
Project description:The fundamental goal of small molecule discovery is to generate chemicals with target functionality. While this often proceeds through structure-based methods, we set out to investigate the practicality of orthogonal methods that leverage the extensive corpus of chemical literature. We hypothesize that a sufficiently large text-derived chemical function dataset would mirror the actual landscape of chemical functionality. Such a landscape would implicitly capture complex physical and biological interactions given that chemical function arises from both a molecule's structure and its interacting partners. To evaluate this hypothesis, we built a Chemical Function (CheF) dataset of patent-derived functional labels. This dataset, comprising 631K molecule-function pairs, was created using an LLM- and embedding-based method to obtain functional labels for approximately 100K molecules from their corresponding 188K unique patents. We carry out a series of analyses demonstrating that the CheF dataset contains a semantically coherent textual representation of the functional landscape congruent with chemical structural relationships, thus approximating the actual chemical function landscape. We then demonstrate that this text-based functional landscape can be leveraged to identify drugs with target functionality using a model able to predict functional profiles from structure alone. We believe that functional label-guided molecular discovery may serve as an orthogonal approach to traditional structure-based methods in the pursuit of designing novel functional molecules.
| S-EPMC10775343 | biostudies-literature
Project description:BackgroundThe wide adoption of social media in daily life renders it a rich and effective resource for conducting near real-time assessments of consumers' perceptions of health services. However, its use in these assessments can be challenging because of the vast amount of data and the diversity of content in social media chatter.ObjectiveThis study aims to develop and evaluate an automatic system involving natural language processing and machine learning to automatically characterize user-posted Twitter data about health services using Medicaid, the single largest source of health coverage in the United States, as an example.MethodsWe collected data from Twitter in two ways: via the public streaming application programming interface using Medicaid-related keywords (Corpus 1) and by using the website's search option for tweets mentioning agency-specific handles (Corpus 2). We manually labeled a sample of tweets in 5 predetermined categories or other and artificially increased the number of training posts from specific low-frequency categories. Using the manually labeled data, we trained and evaluated several supervised learning algorithms, including support vector machine, random forest (RF), naïve Bayes, shallow neural network (NN), k-nearest neighbor, bidirectional long short-term memory, and bidirectional encoder representations from transformers (BERT). We then applied the best-performing classifier to the collected tweets for postclassification analyses to assess the utility of our methods.ResultsWe manually annotated 11,379 tweets (Corpus 1: 9179; Corpus 2: 2200) and used 7930 (69.7%) for training, 1449 (12.7%) for validation, and 2000 (17.6%) for testing. A classifier based on BERT obtained the highest accuracies (81.7%, Corpus 1; 80.7%, Corpus 2) and F1 scores on consumer feedback (0.58, Corpus 1; 0.90, Corpus 2), outperforming the second best classifiers in terms of accuracy (74.6%, RF on Corpus 1; 69.4%, RF on Corpus 2) and F1 score on consumer feedback (0.44, NN on Corpus 1; 0.82, RF on Corpus 2). Postclassification analyses revealed differing intercorpora distributions of tweet categories, with political (400778/628411, 63.78%) and consumer feedback (15073/27337, 55.14%) tweets being the most frequent for Corpus 1 and Corpus 2, respectively.ConclusionsThe broad and variable content of Medicaid-related tweets necessitates automatic categorization to identify topic-relevant posts. Our proposed system presents a feasible solution for automatic categorization and can be deployed and generalized for health service programs other than Medicaid. Annotated data and methods are available for future studies.
| S-EPMC8129876 | biostudies-literature
Project description:ObjectivesThe rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases and highlight research deficiencies. The LitCoin Natural Language Processing (NLP) challenge, organized by the National Center for Advancing Translational Science, aims to evaluate such potential and provides a manually annotated corpus for methodology development and benchmarking.Materials and methodsFor the named entity recognition (NER) task, we utilized ensemble learning to merge predictions from three domain-specific models, namely BioBERT, PubMedBERT, and BioM-ELECTRA, devised a rule-driven detection method for cell line and taxonomy names and annotated 70 more abstracts as additional corpus. We further finetuned the T0pp model, with 11 billion parameters, to boost the performance on relation extraction and leveraged entites' location information (eg, title, background) to enhance novelty prediction performance in relation extraction (RE).ResultsOur pioneering NLP system designed for this challenge secured first place in Phase I-NER and second place in Phase II-relation extraction and novelty prediction, outpacing over 200 teams. We tested OpenAI ChatGPT 3.5 and ChatGPT 4 in a Zero-Shot setting using the same test set, revealing that our finetuned model considerably surpasses these broad-spectrum large language models.Discussion and conclusionOur outcomes depict a robust NLP system excelling in NER and RE across various biomedical entities, emphasizing that task-specific models remain superior to generic large ones. Such insights are valuable for endeavors like knowledge graph development and hypothesis formulation in biomedical research.
| S-EPMC11339500 | biostudies-literature