{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2020-03-23T00:58:30.381046+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 7, "enabled": true, "entries": { "frequent_bigrams.csv": { "checksum": "md5:2d45b4fa0704e5ad8833f32620ed1733", "ext": "csv", "id": "891562e8-6299-4a25-97b1-9b97621cc813", "key": "frequent_bigrams.csv", "metadata": null, "mimetype": "text/csv", "size": 19628 }, "frequent_terms.csv": { "checksum": "md5:cf22046acb6e1b51bedc8de36a7f2833", "ext": "csv", "id": "c01c6a03-dac4-40cd-9c9d-84b995aff9b2", "key": "frequent_terms.csv", "metadata": null, "mimetype": "text/csv", "size": 11946 }, "frequent_trigrams.csv": { "checksum": "md5:c810eb0e9bbbd35e13de684947983a85", "ext": "csv", "id": "674cc02c-fe93-4ef2-ba9e-23aad048f670", "key": "frequent_trigrams.csv", "metadata": null, "mimetype": "text/csv", "size": 25220 }, "full_dataset-clean.tsv": { "checksum": "md5:bf4f5e5ea3c27da397c83bbabcdee948", "ext": "tsv", "id": "06817a70-17d7-4265-95f8-0d6b2746d04a", "key": "full_dataset-clean.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 286149421 }, "full_dataset.tsv": { "checksum": "md5:9f376c690363289587a8681ea69e2107", "ext": "tsv", "id": "8a5f950e-0ed2-4297-8686-242bcc0dac0e", "key": "full_dataset.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 1561202713 }, "statistics-full_dataset-clean.tsv": { "checksum": "md5:6a3e65339b3790032520aca7100cfbf3", "ext": "tsv", "id": "e6c17a67-f200-4bab-8ba1-27d133822410", "key": "statistics-full_dataset-clean.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 1109 }, "statistics-full_dataset.tsv": { "checksum": "md5:aad7b0a2ff6d605b5a6da2077b53180e", "ext": "tsv", "id": "8e8fd72d-00da-4d4b-a523-f1a94aa09bfc", "key": "statistics-full_dataset.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 1172 } }, "order": [], "total_bytes": 1847411209 }, "id": "3723940", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/3723940/access", "access_links": "https://zenodo.org/api/records/3723940/access/links", "access_request": "https://zenodo.org/api/records/3723940/access/request", "access_users": "https://zenodo.org/api/records/3723940/access/users", "archive": "https://zenodo.org/api/records/3723940/files-archive", "archive_media": "https://zenodo.org/api/records/3723940/media-files-archive", "communities": "https://zenodo.org/api/records/3723940/communities", "communities-suggestions": "https://zenodo.org/api/records/3723940/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.3723940", "draft": "https://zenodo.org/api/records/3723940/draft", "files": "https://zenodo.org/api/records/3723940/files", "latest": "https://zenodo.org/api/records/3723940/versions/latest", "latest_html": "https://zenodo.org/records/3723940/latest", "media_files": "https://zenodo.org/api/records/3723940/media-files", "parent": "https://zenodo.org/api/records/3723939", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.3723939", "parent_html": "https://zenodo.org/records/3723939", "requests": "https://zenodo.org/api/records/3723940/requests", "reserve_doi": "https://zenodo.org/api/records/3723940/draft/pids/doi", "self": "https://zenodo.org/api/records/3723940", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.3723940", "self_html": "https://zenodo.org/records/3723940", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:3723940/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:3723940/sequence/default", "versions": "https://zenodo.org/api/records/3723940/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "additional_descriptions": [ { "description": "This dataset will be updated bi-weekly at least with additional tweets", "type": { "id": "notes", "title": { "de": "Anmerkungen", "en": "Notes" } } } ], "creators": [ { "affiliations": [ { "name": "Georgia State University" } ], "person_or_org": { "family_name": "Banda", "given_name": "Juan M.", "identifiers": [ { "identifier": "0000-0001-8499-824X", "scheme": "orcid" } ], "name": "Banda, Juan M.", "type": "personal" } }, { "affiliations": [ { "name": "Georgia State University" } ], "person_or_org": { "family_name": "Tekumalla", "given_name": "Ramya", "identifiers": [ { "identifier": "0000-0002-1606-4856", "scheme": "orcid" } ], "name": "Tekumalla, Ramya", "type": "personal" } } ], "description": "
Due to the relevance of the COVID-19 global pandemic, we are releasing our dataset of tweets acquired from the Twitter Stream related to COVID-19 chatter. The first 9 weeks of data (from January 1st, 2020 to March 11th, 2020) contain very low tweet counts as we filtered other data we were collecting for other research purposes, however, one can see the dramatic increase as the awareness for the virus spread. Dedicated data gathering started from March 11th to March 22nd which yielded over 4 million tweets a day.
\n\nThe data collected from the stream captures all languages, but the higher prevalence are: English, Spanish, and French. We release all tweets and retweets on the full_dataset.tsv file (40,823,816 unique tweets), and a cleaned version with no retweets on the full_dataset-clean.tsv file (7,479,940 unique tweets). There are several practical reasons for us to leave the retweets, tracing important tweets and their dissemination is one of them. For NLP tasks we provide the top 1000 frequent terms in frequent_terms.csv, the top 1000 bigrams in frequent_bigrams.csv, and the top 1000 trigrams in frequent_trigrams.csv. Some general statistics per day are included for both datasets in the statistics-full_dataset.tsv and statistics-full_dataset-clean.tsv files.
\n\nMore details can be found (and will be updated faster at: https://github.com/thepanacealab/covid19_twitter)
\n\nAs always, the tweets distributed here are only tweet identifiers (with date and time added) due to the terms and conditions of Twitter to re-distribute Twitter data. The need to be hydrated to be used.
", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2020-03-23", "publisher": "Zenodo", "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "" }, "id": "other-pd", "title": { "en": "Other (Public Domain)" } } ], "subjects": [ { "subject": "social media" }, { "subject": "twitter" }, { "subject": "nlp" }, { "subject": "covid-19" }, { "subject": "covid19" } ], "title": "A Twitter Dataset of 40+ million tweets related to COVID-19", "version": "1.0" }, "parent": { "access": { "owned_by": { "user": 95208 } }, "communities": { "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2020-03-16T11:40:44.487619+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "10f33f78-3f29-41b6-bb10-f757a8f03cb8", "links": {}, "metadata": { "curation_policy": "The Coronavirus Disease Research Community - COVID-19 is curated by a selected team of experts nominated by OpenAIRE* (see list below). Each time a Zenodo user wants to add a record into the community, an email is sent to the curators that will decide whether to include the record or not.
\r\n\r\nOnly records that may be relevant to the Corona Virus Disease (COVID-19) or the SARS-CoV-2 should be included in this community. The Community curators are not able to edit records, therefore they may ask the corresponding authors to modify the record metadata when necessary, to provide the readers/users with more detailed information according to the FAIR principle of Open Science.
\r\n\r\nIf after its acceptance, a record is subsequently found not to be compliant, we reserve the right to remove it from the community.
\r\n\r\nThe curation team is reachable through the following email address for further clarification or information: covid19@openaire.eu.
\r\n\r\nCurator List:
\r\n\r\n* OpenAIRE: open access and open science training and support since 2009. OpenAIRE is the largest aggregator of European Commission funded research outputs and beyond, also delivering on-demand services for research communities.
\r\n", "page": "This community collects research outputs that may be relevant to the Coronavirus Disease (COVID-19) or the SARS-CoV-2. Scientists are encouraged to upload their outcome in this collection to facilitate sharing and discovery of information. Although Open Access articles and datasets are recommended, also closed and restricted access material are accepted. All types of research outputs can be included in this Community (Publication, Poster, Presentation, Dataset, Image, Video/Audio, Software, Lesson, Other).
\r\n\r\nThe recent Corona Virus Disease (COVID-19) outbreak is requiring unseen efforts of collaboration of the scientific community that need to act fast and to share results in an unpredictable manner. In order to facilitate the Scientist efforts, this community was created to collect all research results that could be relevant for the scientific community working on the Corona Virus Disease (COVID-19) and SARS-CoV-2.
\r\n\r\nAlthough Open Access articles and datasets are recommended, also closed and restricted access material are accepted. All types of research outputs can be included in this Community (Publication, Poster, Presentation, Dataset, Image, Video/Audio, Software, Lesson, Other).
\r\n\r\nWhen depositing a resource that is linked to other resources (not limited to the records deposited in Zenodo but also in other repositories), please make sure that your record is linked to all the other related elements already available, in order to adhere to the FAIR principles of Open Science to maximise the reusability of research results.
\r\n\r\n", "title": "Coronavirus Disease Research Community - COVID-19" }, "revision_id": 0, "slug": "covid-19", "updated": "2021-02-23T14:39:53.029415+00:00" }, { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2020-04-10T21:19:49.352703+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "977b3a0f-175d-465c-83dd-aa20d2e98a1d", "links": {}, "metadata": { "curation_policy": "", "description": "Resources curated in the context of BioHackathon projects.", "page": "", "title": "BioHackathon" }, "revision_id": 0, "slug": "biohackathon", "updated": "2023-06-27T14:09:12.164017+00:00" } ], "ids": [ "10f33f78-3f29-41b6-bb10-f757a8f03cb8", "977b3a0f-175d-465c-83dd-aa20d2e98a1d" ] }, "id": "3723939", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3723939", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3723940", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:3723940", "provider": "oai" } }, "revision_id": 181, "stats": { "all_versions": { "data_volume": 310515393151554.0, "downloads": 225127, "unique_downloads": 61272, "unique_views": 292802, "views": 320111 }, "this_version": { "data_volume": 3599709543689.0, "downloads": 8336, "unique_downloads": 4429, "unique_views": 15514, "views": 17839 } }, "status": "published", "updated": "2023-04-17T12:14:52.940675+00:00", "versions": { "index": 1, "is_latest": false } }