{"id":"https://openalex.org/W4394657404","doi":"https://doi.org/10.48550/arxiv.2003.13900","title":"A large-scale Twitter dataset for drug safety applications mined from publicly existing resources","display_name":"A large-scale Twitter dataset for drug safety applications mined from publicly existing resources","publication_year":2020,"publication_date":"2020-03-31","ids":{"openalex":"https://openalex.org/W4394657404","doi":"https://doi.org/10.48550/arxiv.2003.13900"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2003.13900","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13900","pdf_url":"https://arxiv.org/pdf/2003.13900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.13900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043622075","display_name":"Ramya Tekumalla","orcid":"https://orcid.org/0000-0002-1606-4856","observed_orcids":["https://orcid.org/0000-0002-1606-4856","https://orcid.org/0000-0002-2533-0407"]},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tekumalla, Ramya","raw_affiliation_strings":["Department of Computer Science Georgia State University Atlanta GA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Georgia State University Atlanta GA USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011590035","display_name":"Juan M. Banda","orcid":"https://orcid.org/0000-0001-8499-824X","observed_orcids":["https://orcid.org/0000-0001-8499-824X","https://orcid.org/0000-0003-3864-0241"]},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Banda, Juan M.","raw_affiliation_strings":["Department of Computer Science Georgia State University Atlanta GA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Georgia State University Atlanta GA USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/twitter-dataset","display_name":"Twitter dataset","score":0.7509999871253967},{"id":"https://openalex.org/keywords/pharmacovigilance","display_name":"pharmacovigilance","score":0.8870000243186951},{"id":"https://openalex.org/keywords/adverse-drug-reactions","display_name":"adverse drug reactions","score":0.9980000257492065},{"id":"https://openalex.org/keywords/drug-safety","display_name":"drug safety","score":0.9399999976158142},{"id":"https://openalex.org/keywords/social-media-mining","display_name":"social media mining","score":0.7609999775886536},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/tweet-filtering","display_name":"tweet filtering","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.649013102054596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5055272579193115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4779917597770691},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.355970561504364},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3458743095397949},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16534170508384705},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1136186420917511}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2003.13900","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13900","pdf_url":"https://arxiv.org/pdf/2003.13900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2003.13900","doi":"https://doi.org/10.48550/arxiv.2003.13900","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.13900","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.13900","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13900","pdf_url":"https://arxiv.org/pdf/2003.13900","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8560000061988831,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394657404.pdf","grobid_xml":"https://content.openalex.org/works/W4394657404.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1969096316","https://openalex.org/W1975587682","https://openalex.org/W2009890917","https://openalex.org/W2073386434","https://openalex.org/W2086869155","https://openalex.org/W2102742655","https://openalex.org/W2171469118","https://openalex.org/W2356882517","https://openalex.org/W2473355215","https://openalex.org/W2475102260","https://openalex.org/W2504291398","https://openalex.org/W2517728584","https://openalex.org/W2556166063","https://openalex.org/W4206713405","https://openalex.org/W4246053374"],"related_works":["https://openalex.org/W3037156224","https://openalex.org/W2007628554","https://openalex.org/W2417936835","https://openalex.org/W3167995209","https://openalex.org/W2787067835","https://openalex.org/W6902488214","https://openalex.org/W4409145441","https://openalex.org/W2787778394","https://openalex.org/W2995441112","https://openalex.org/W7097145198"],"abstract_inverted_index":{"With":[0,43],"the":[1,16,23,96,114,129,158],"increase":[2],"in":[3,15,77],"popularity":[4],"of":[5,18,25,49,89,98,104,132,137],"deep":[6],"learning":[7,126],"models":[8],"for":[9,22,35,122,141,162],"natural":[10],"language":[11],"processing":[12],"(NLP)":[13],"tasks,":[14],"field":[17],"Pharmacovigilance,":[19],"more":[20,71,73,90],"specifically":[21],"identification":[24],"Adverse":[26],"Drug":[27],"Reactions":[28],"(ADRs),":[29],"there":[30],"is":[31],"an":[32],"inherent":[33],"need":[34],"large-scale":[36],"social-media":[37],"datasets":[38,112],"aimed":[39],"at":[40],"such":[41],"tasks.":[42],"most":[44],"researchers":[45,163],"allocating":[46],"large":[47,102],"amounts":[48],"time":[50],"to":[51,153,164],"crawl":[52],"Twitter":[53],"or":[54],"buying":[55],"expensive":[56],"pre-curated":[57],"datasets,":[58],"then":[59,117],"manually":[60,110],"annotating":[61],"by":[62],"humans,":[63],"these":[64],"approaches":[65],"do":[66],"not":[67],"scale":[68],"well":[69],"as":[70],"and":[72,148,157],"data":[74],"keeps":[75],"flowing":[76],"Twitter.":[78],"In":[79],"this":[80,155],"work":[81],"we":[82,116],"re-purpose":[83],"a":[84,100,133],"publicly":[85,134],"available":[86,135],"archived":[87],"dataset":[88,103,136,156],"than":[91],"9.4":[92],"billion":[93],"Tweets":[94],"with":[95,128],"objective":[97],"creating":[99],"very":[101],"drug":[105],"usage-related":[106],"tweets.":[107],"Using":[108],"existing":[109],"curated":[111],"from":[113],"literature,":[115],"validate":[118],"our":[119],"filtered":[120],"tweets":[121,140],"relevance":[123],"using":[124],"machine":[125],"methods,":[127],"end":[130],"result":[131],"1,181,993":[138],"million":[139],"public":[142],"use.":[143,165],"We":[144],"provide":[145],"all":[146],"code":[147],"detailed":[149],"procedure":[150],"on":[151],"how":[152],"extract":[154],"selected":[159],"tweet":[160],"ids":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-04-11T00:00:00"}