{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2022-04-03T15:09:14.716392+00:00", "custom_fields": { "journal:journal": { "issue": "3", "pages": "315-324", "title": "Epidemiologia", "volume": "2" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 10, "enabled": true, "entries": { "emojis.zip": { "checksum": "md5:2b9da5e692e043b63d3beaeb7395dc8d", "ext": "zip", "id": "381c27ea-18e6-4225-b938-e9574c0eaeeb", "key": "emojis.zip", "metadata": null, "mimetype": "application/zip", "size": 12097851 }, "frequent_bigrams.csv": { "checksum": "md5:e9ae06b05c539ffe47a827a40fb45211", "ext": "csv", "id": "7aac3a8c-285c-489a-aed7-9e2a026c582b", "key": "frequent_bigrams.csv", "metadata": null, "mimetype": "text/csv", "size": 18247 }, "frequent_terms.csv": { "checksum": "md5:c94903fc2fa9f5f8e4e09141f2d50205", "ext": "csv", "id": "8de9c1fe-faff-4e09-8557-034ec2c5facd", "key": "frequent_terms.csv", "metadata": null, "mimetype": "text/csv", "size": 11600 }, "frequent_trigrams.csv": { "checksum": "md5:458a5cdfd61616c8dba7540661fb404b", "ext": "csv", "id": "2817e7a5-65e4-4610-aee9-37ef09080ab2", "key": "frequent_trigrams.csv", "metadata": null, "mimetype": "text/csv", "size": 24847 }, "full_dataset-statistics.tsv": { "checksum": "md5:abf06d60d82cba98b1cf3fe75e9178bc", "ext": "tsv", "id": "5d0896ed-d5b8-4a7a-bba1-9650543a7e78", "key": "full_dataset-statistics.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 15260 }, "full_dataset.tsv.gz": { "checksum": "md5:ff25b0d2330f7cf50ef60ab7ad54cef6", "ext": "gz", "id": "aca1f67d-3451-4c7a-9484-cc5c9e9c5259", "key": "full_dataset.tsv.gz", "metadata": null, "mimetype": "application/gzip", "size": 11348650373 }, "full_dataset_clean-statistics.tsv": { "checksum": "md5:0c3c4f7cadd7c8886255a3507364f869", "ext": "tsv", "id": "718c8867-f51c-4b52-82a9-f23e22544058", "key": "full_dataset_clean-statistics.tsv", "metadata": null, "mimetype": "text/tab-separated-values", "size": 14753 }, "full_dataset_clean.tsv.gz": { "checksum": "md5:e487ba256c8713a736aad4f103c214f0", "ext": "gz", "id": "7c04a238-fb4d-424d-a6a4-ea6b4e16ad53", "key": "full_dataset_clean.tsv.gz", "metadata": null, "mimetype": "application/gzip", "size": 3275625868 }, "hashtags.zip": { "checksum": "md5:73311f70108232851bd3dae0618226a3", "ext": "zip", "id": "dd95f225-0560-41e7-9a66-e6749c4b4b1e", "key": "hashtags.zip", "metadata": null, "mimetype": "application/zip", "size": 187412267 }, "mentions.zip": { "checksum": "md5:92b45b49556eeaaedde20981fcc4db3f", "ext": "zip", "id": "da573e92-a79a-49d7-a02c-bcd6ecefc8db", "key": "mentions.zip", "metadata": null, "mimetype": "application/zip", "size": 311841477 } }, "order": [], "total_bytes": 15135712543 }, "id": "6409765", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/6409765/access", "access_links": "https://zenodo.org/api/records/6409765/access/links", "access_request": "https://zenodo.org/api/records/6409765/access/request", "access_users": "https://zenodo.org/api/records/6409765/access/users", "archive": "https://zenodo.org/api/records/6409765/files-archive", "archive_media": "https://zenodo.org/api/records/6409765/media-files-archive", "communities": "https://zenodo.org/api/records/6409765/communities", "communities-suggestions": "https://zenodo.org/api/records/6409765/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.6409765", "draft": "https://zenodo.org/api/records/6409765/draft", "files": "https://zenodo.org/api/records/6409765/files", "latest": "https://zenodo.org/api/records/6409765/versions/latest", "latest_html": "https://zenodo.org/records/6409765/latest", "media_files": "https://zenodo.org/api/records/6409765/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/6409765/requests", "reserve_doi": "https://zenodo.org/api/records/6409765/draft/pids/doi", "self": "https://zenodo.org/api/records/6409765", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.6409765", "self_html": "https://zenodo.org/records/6409765", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:6409765/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:6409765/sequence/default", "versions": "https://zenodo.org/api/records/6409765/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, look at the github repo for these updates.\nRelease: We have standardized the name of the resource to match our pre-print manuscript and to not have to update it every week.", "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" } }, { "affiliations": [ { "name": "University of Missouri" } ], "person_or_org": { "family_name": "Wang", "given_name": "Guanyu", "name": "Wang, Guanyu", "type": "personal" } }, { "affiliations": [ { "name": "Universitat Aut\u00f2noma de Barcelona" } ], "person_or_org": { "family_name": "Yu", "given_name": "Jingyuan", "name": "Yu, Jingyuan", "type": "personal" } }, { "affiliations": [ { "name": "Carl von Ossietzky Universit\u00e4t Oldenburg" } ], "person_or_org": { "family_name": "Liu", "given_name": "Tuo", "name": "Liu, Tuo", "type": "personal" } }, { "affiliations": [ { "name": "Universit\u00e4t Duisburg-Essen" } ], "person_or_org": { "family_name": "Ding", "given_name": "Yuning", "name": "Ding, Yuning", "type": "personal" } }, { "affiliations": [ { "name": "NRU HSE" } ], "person_or_org": { "family_name": "Artemova", "given_name": "Katya", "name": "Artemova, Katya", "type": "personal" } }, { "affiliations": [ { "name": "KFU" } ], "person_or_org": { "family_name": "Tutubalina", "given_name": "Elena", "name": "Tutubalina, Elena", "type": "personal" } }, { "affiliations": [ { "name": "Georgia State University" } ], "person_or_org": { "family_name": "Chowell", "given_name": "Gerardo", "identifiers": [ { "identifier": "0000-0003-2194-2251", "scheme": "orcid" } ], "name": "Chowell, Gerardo", "type": "personal" } } ], "description": "
Version 108 of the dataset. The peer-reviewed publication for this dataset has now been published in Epidemiologia an MDPI journal, and can be accessed here: https://doi.org/10.3390/epidemiologia2030024. Please cite this when using the dataset.
\n\nDue 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. Since our first release we have received additional data from our new collaborators, allowing this resource to grow to its current size. Dedicated data gathering started from March 11th yielding over 4 million tweets a day. We have added additional data provided by our new collaborators from January 27th to March 27th, to provide extra longitudinal coverage. Version 10 added ~1.5 million tweets in the Russian language collected between January 1st and May 8th, gracefully provided to us by: Katya Artemova (NRU HSE) and Elena Tutubalina (KFU). From version 12 we have included daily hashtags, mentions and emoijis and their frequencies the respective zip files. From version 14 we have included the tweet identifiers and their respective language for the clean version of the dataset. Since version 20 we have included language and place location for all tweets.
\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 (1,327,342,069 unique tweets), and a cleaned version with no retweets on the full_dataset-clean.tsv file (342,712,664 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 full_dataset-statistics.tsv and full_dataset-clean-statistics.tsv files. For more statistics and some visualizations visit: http://www.panacealab.org/covid19/
\n\nMore details can be found (and will be updated faster at: https://github.com/thepanacealab/covid19_twitter) and our pre-print about the dataset (https://arxiv.org/abs/2004.03688)
\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 ONLY for research purposes. They need to be hydrated to be used.
", "identifiers": [ { "identifier": "10.3390/epidemiologia2030024", "scheme": "doi" }, { "identifier": "https://github.com/thepanacealab/covid19_twitter", "scheme": "url" } ], "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2022-04-03", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "http://www.panacealab.org/covid19/", "relation_type": { "id": "iscontinuedby", "title": { "de": "Wird fortgesetzt durch", "en": "Is continued by" } }, "resource_type": { "id": "other", "title": { "de": "Sonstige", "en": "Other" } }, "scheme": "url" }, { "identifier": "https://arxiv.org/abs/2004.03688", "relation_type": { "id": "issupplementto", "title": { "de": "Erg\u00e4nzt", "en": "Is supplement to" } }, "resource_type": { "id": "publication-preprint", "title": { "de": "Preprint", "en": "Preprint" } }, "scheme": "url" } ], "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 large-scale COVID-19 Twitter chatter dataset for open scientific research - an international collaboration", "version": "108" }, "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.6409765", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:6409765", "provider": "oai" } }, "revision_id": 58, "stats": { "all_versions": { "data_volume": 310516682600486.0, "downloads": 225129, "unique_downloads": 61274, "unique_views": 292846, "views": 320157 }, "this_version": { "data_volume": 406651524043.0, "downloads": 274, "unique_downloads": 152, "unique_views": 872, "views": 991 } }, "status": "published", "updated": "2023-04-17T12:15:17.485184+00:00", "versions": { "index": 109, "is_latest": false } }