{"data":{"id":"10.6084/m9.figshare.4052331.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.4052331.v1","prefix":"10.6084","suffix":"m9.figshare.4052331.v1","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Lampos, Vasileios","nameType":"Personal","givenName":"Vasileios","familyName":"Lampos","affiliation":[],"nameIdentifiers":[{"schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-8555-2063","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"UK Twitter word embeddings"}],"publisher":"figshare","container":{},"publicationYear":2016,"subjects":[{"subject":"Applied Computer Science"},{"subject":"80107 Natural Language Processing","subjectScheme":"FOR"},{"subject":"FOS: Computer and information sciences","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Computer and information sciences","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"80704 Information Retrieval and Web Search","subjectScheme":"FOR"},{"subject":"FOS: Media and communications","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Media and communications","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"170203 Knowledge Representation and Machine Learning","subjectScheme":"FOR"},{"subject":"FOS: Psychology","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Psychology","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"170205 Neurocognitive Patterns and Neural Networks","subjectScheme":"FOR"}],"contributors":[],"dates":[{"date":"2016-10-22","dateType":"Created"},{"date":"2016-10-22","dateType":"Updated"},{"date":"2016","dateType":"Issued"}],"language":null,"types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.4052331","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["229206728 Bytes"],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"\u003cb\u003eWord embeddings trained on Twitter content geo-located in the United Kingdom\u003c/b\u003e\u003cbr\u003eThe total number of tweets used was approximately 215 million, dated from February 1, 2014 to March 31, 2016. Word2vec has been applied as implemented in the gensim library (https://radimrehurek.com/gensim/).\u003cbr\u003e\u003cb\u003eSettings:\u003c/b\u003e Continuous bag-of-words representation (CBOW), the entirety of a tweet as a window, negative sampling (5 noise words), and a dimensionality of 512. \u003cbr\u003eAfter filtering out words with less than 500 occurrences, an embedding corpus of 137,421 unigrams was obtained (see \u003cb\u003evocabulary.txt\u003c/b\u003e). The corresponding 512-dimensional embeddings are held in \u003cb\u003evectors.zip\u003c/b\u003e.\u003cbr\u003e","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KPHJlc291cmNlIHhtbG5zPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCIgeG1sbnM6eHNpPSJodHRwOi8vd3d3LnczLm9yZy8yMDAxL1hNTFNjaGVtYS1pbnN0YW5jZSIgeHNpOnNjaGVtYUxvY2F0aW9uPSJodHRwOi8vZGF0YWNpdGUub3JnL3NjaGVtYS9rZXJuZWwtNCBodHRwOi8vc2NoZW1hLmRhdGFjaXRlLm9yZy9tZXRhL2tlcm5lbC00LjEvbWV0YWRhdGEueHNkIj4KICA8aWRlbnRpZmllciBpZGVudGlmaWVyVHlwZT0iRE9JIj4xMC42MDg0L005LkZJR1NIQVJFLjQwNTIzMzEuVjE8L2lkZW50aWZpZXI+CiAgPGNyZWF0b3JzPgogICAgPGNyZWF0b3I+CiAgICAgIDxjcmVhdG9yTmFtZT5WYXNpbGVpb3MgTGFtcG9zPC9jcmVhdG9yTmFtZT4KICAgICAgPG5hbWVJZGVudGlmaWVyIG5hbWVJZGVudGlmaWVyU2NoZW1lPSJPUkNJRCIgc2NoZW1lVVJJPSJodHRwOi8vb3JjaWQub3JnIj4wMDAwLTAwMDEtODU1NS0yMDYzPC9uYW1lSWRlbnRpZmllcj4KICAgIDwvY3JlYXRvcj4KICA8L2NyZWF0b3JzPgogIDx0aXRsZXM+CiAgICA8dGl0bGU+VUsgVHdpdHRlciB3b3JkIGVtYmVkZGluZ3M8L3RpdGxlPgogIDwvdGl0bGVzPgogIDxkZXNjcmlwdGlvbnM+CiAgICA8ZGVzY3JpcHRpb24gZGVzY3JpcHRpb25UeXBlPSJBYnN0cmFjdCI+Jmx0O2RpdiZndDsmbHQ7YiZndDtXb3JkIGVtYmVkZGluZ3MgdHJhaW5lZCBvbiBUd2l0dGVyIGNvbnRlbnQgZ2VvLWxvY2F0ZWQgaW4gdGhlIFVuaXRlZCBLaW5nZG9tJmx0Oy9iJmd0OyZsdDsvZGl2Jmd0OyZsdDtkaXYmZ3Q7Jmx0O2JyJmd0O1RoZSB0b3RhbCBudW1iZXIgb2YgdHdlZXRzIHVzZWQgd2FzIGFwcHJveGltYXRlbHkgMjE1IG1pbGxpb24sIGRhdGVkIGZyb20gRmVicnVhcnkgMSwgMjAxNCB0byBNYXJjaCAzMSwgMjAxNi4gV29yZDJ2ZWMgaGFzIGJlZW4gYXBwbGllZCBhcyBpbXBsZW1lbnRlZCBpbiB0aGUgZ2Vuc2ltIGxpYnJhcnkgKGh0dHBzOi8vcmFkaW1yZWh1cmVrLmNvbS9nZW5zaW0vKS4mbHQ7L2RpdiZndDsmbHQ7ZGl2Jmd0OyZsdDticiZndDsmbHQ7L2RpdiZndDsmbHQ7ZGl2Jmd0OyZsdDtiJmd0O1NldHRpbmdzOiZsdDsvYiZndDsgQ29udGludW91cyBiYWctb2Ytd29yZHMgcmVwcmVzZW50YXRpb24gKENCT1cpLCB0aGUgZW50aXJldHkgb2YgYSB0d2VldCBhcyBhIHdpbmRvdywgbmVnYXRpdmUgc2FtcGxpbmcgKDUgbm9pc2Ugd29yZHMpLCBhbmQgYSBkaW1lbnNpb25hbGl0eSBvZiA1MTIuwqAmbHQ7L2RpdiZndDsmbHQ7ZGl2Jmd0OyZsdDticiZndDsmbHQ7L2RpdiZndDsmbHQ7ZGl2Jmd0O0FmdGVyIGZpbHRlcmluZyBvdXQgd29yZHMgd2l0aCBsZXNzIHRoYW4gNTAwIG9jY3VycmVuY2VzLCBhbiBlbWJlZGRpbmcgY29ycHVzIG9mIDEzNyw0MjEgdW5pZ3JhbXMgd2FzIG9idGFpbmVkIChzZWUgJmx0O2ImZ3Q7dm9jYWJ1bGFyeS50eHQmbHQ7L2ImZ3Q7KS4gVGhlIGNvcnJlc3BvbmRpbmcgNTEyLWRpbWVuc2lvbmFsIGVtYmVkZGluZ3MgYXJlIGhlbGQgaW7CoCZsdDtiJmd0O3ZlY3RvcnMuemlwJmx0Oy9iJmd0Oy4mbHQ7L2RpdiZndDsmbHQ7ZGl2Jmd0OyZsdDticiZndDsmbHQ7L2RpdiZndDs8L2Rlc2NyaXB0aW9uPgogIDwvZGVzY3JpcHRpb25zPgogIDxzdWJqZWN0cz4KICAgIDxzdWJqZWN0PkFwcGxpZWQgQ29tcHV0ZXIgU2NpZW5jZTwvc3ViamVjdD4KICAgIDxzdWJqZWN0IHNjaGVtZVVSST0iaHR0cDovL3d3dy5hYnMuZ292LmF1L2F1c3N0YXRzL2Fic0AubnNmLzAvNkJCNDI3QUI5Njk2QzIyNUNBMjU3NDE4MDAwNDQ2M0UiIHN1YmplY3RTY2hlbWU9IkZPUiI+ODAxMDcgTmF0dXJhbCBMYW5ndWFnZSBQcm9jZXNzaW5nPC9zdWJqZWN0PgogICAgPHN1YmplY3Qgc2NoZW1lVVJJPSJodHRwOi8vd3d3LmFicy5nb3YuYXUvYXVzc3RhdHMvYWJzQC5uc2YvMC82QkI0MjdBQjk2OTZDMjI1Q0EyNTc0MTgwMDA0NDYzRSIgc3ViamVjdFNjaGVtZT0iRk9SIj44MDcwNCBJbmZvcm1hdGlvbiBSZXRyaWV2YWwgYW5kIFdlYiBTZWFyY2g8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjE3MDIwMyBLbm93bGVkZ2UgUmVwcmVzZW50YXRpb24gYW5kIE1hY2hpbmUgTGVhcm5pbmc8L3N1YmplY3Q+CiAgICA8c3ViamVjdCBzY2hlbWVVUkk9Imh0dHA6Ly93d3cuYWJzLmdvdi5hdS9hdXNzdGF0cy9hYnNALm5zZi8wLzZCQjQyN0FCOTY5NkMyMjVDQTI1NzQxODAwMDQ0NjNFIiBzdWJqZWN0U2NoZW1lPSJGT1IiPjE3MDIwNSBOZXVyb2NvZ25pdGl2ZSBQYXR0ZXJucyBhbmQgTmV1cmFsIE5ldHdvcmtzPC9zdWJqZWN0PgogIDwvc3ViamVjdHM+CiAgPHB1Ymxpc2hlcj5maWdzaGFyZTwvcHVibGlzaGVyPgogIDxwdWJsaWNhdGlvblllYXI+MjAxNjwvcHVibGljYXRpb25ZZWFyPgogIDxkYXRlcz4KICAgIDxkYXRlIGRhdGVUeXBlPSJDcmVhdGVkIj4yMDE2LTEwLTIyPC9kYXRlPgogICAgPGRhdGUgZGF0ZVR5cGU9IlVwZGF0ZWQiPjIwMTYtMTAtMjI8L2RhdGU+CiAgPC9kYXRlcz4KICA8cmVzb3VyY2VUeXBlIHJlc291cmNlVHlwZUdlbmVyYWw9IkRhdGFzZXQiPkRhdGFzZXQ8L3Jlc291cmNlVHlwZT4KICA8c2l6ZXM+CiAgICA8c2l6ZT4yMjkyMDY3MjggQnl0ZXM8L3NpemU+CiAgPC9zaXplcz4KICA8cmVsYXRlZElkZW50aWZpZXJzPgogICAgPHJlbGF0ZWRJZGVudGlmaWVyIHJlbGF0ZWRJZGVudGlmaWVyVHlwZT0iRE9JIiByZWxhdGlvblR5cGU9IklzSWRlbnRpY2FsVG8iPjEwLjYwODQvbTkuZmlnc2hhcmUuNDA1MjMzMTwvcmVsYXRlZElkZW50aWZpZXI+CiAgPC9yZWxhdGVkSWRlbnRpZmllcnM+CiAgPHJpZ2h0c0xpc3Q+CiAgICA8cmlnaHRzIHJpZ2h0c1VSST0iaHR0cHM6Ly9jcmVhdGl2ZWNvbW1vbnMub3JnL2xpY2Vuc2VzL2J5LzQuMC8iPkNDIEJZIDQuMDwvcmlnaHRzPgogIDwvcmlnaHRzTGlzdD4KPC9yZXNvdXJjZT4=","url":"https://figshare.com/articles/dataset/UK_Twitter_word_embeddings/4052331/1","contentUrl":null,"metadataVersion":2,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":6,"viewsOverTime":[{"yearMonth":"2025-03","total":1},{"yearMonth":"2025-03","total":1},{"yearMonth":"2025-05","total":3},{"yearMonth":"2026-05","total":1}],"downloadCount":1,"downloadsOverTime":[{"yearMonth":"2025-03","total":0},{"yearMonth":"2025-03","total":0},{"yearMonth":"2025-05","total":1},{"yearMonth":"2026-05","total":0}],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2016-10-22T16:36:26.000Z","registered":"2016-10-22T16:36:27.000Z","published":"2016","updated":"2025-06-01T07:10:57.000Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}},"provider":{"data":{"id":"otjm","type":"providers"}},"media":{"data":{"id":"10.6084/m9.figshare.4052331.v1","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}