{"id":"https://openalex.org/W4320024265","doi":"https://doi.org/10.1109/bigdata55660.2022.10020214","title":"TweetDIS: A Large Twitter Dataset for Natural Disasters Built using Weak Supervision","display_name":"TweetDIS: A Large Twitter Dataset for Natural Disasters Built using Weak Supervision","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024265","doi":"https://doi.org/10.1109/bigdata55660.2022.10020214"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020214","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043622075","display_name":"Ramya Tekumalla","orcid":"https://orcid.org/0000-0002-1606-4856"},"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":true,"raw_author_name":"Ramya Tekumalla","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,USA","Department of Computer Science, Georgia State University, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,USA","institution_ids":["https://openalex.org/I181565077"]},{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, 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"},"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":"Juan M. Banda","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,USA","Department of Computer Science, Georgia State University, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,USA","institution_ids":["https://openalex.org/I181565077"]},{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043622075"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":4.798,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96129032,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4816","last_page":"4823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9909999966621399,"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"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9909999966621399,"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"}},{"id":"https://openalex.org/T11121","display_name":"Public Relations and Crisis Communication","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13018","display_name":"Seismology and Earthquake Studies","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-disaster","display_name":"Natural disaster","score":0.7147182822227478},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7023932933807373},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7013344764709473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.66511470079422},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5128648281097412},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4949743151664734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47797390818595886},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46945613622665405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32047125697135925},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20746782422065735},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20604407787322998},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12053552269935608}],"concepts":[{"id":"https://openalex.org/C166566181","wikidata":"https://www.wikidata.org/wiki/Q8065","display_name":"Natural disaster","level":2,"score":0.7147182822227478},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7023932933807373},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7013344764709473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66511470079422},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5128648281097412},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4949743151664734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47797390818595886},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46945613622665405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32047125697135925},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20746782422065735},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20604407787322998},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12053552269935608},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020214","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W10004740","https://openalex.org/W1579815680","https://openalex.org/W1973921702","https://openalex.org/W2074950806","https://openalex.org/W2101234009","https://openalex.org/W2110785023","https://openalex.org/W2186120071","https://openalex.org/W2231433198","https://openalex.org/W2297338375","https://openalex.org/W2302501749","https://openalex.org/W2402454488","https://openalex.org/W2547490807","https://openalex.org/W2742970053","https://openalex.org/W2751803764","https://openalex.org/W2753820901","https://openalex.org/W2757243104","https://openalex.org/W2768174831","https://openalex.org/W2898147691","https://openalex.org/W2912515299","https://openalex.org/W2937423263","https://openalex.org/W2962707464","https://openalex.org/W2979826702","https://openalex.org/W2997517168","https://openalex.org/W3014211423","https://openalex.org/W3016387666","https://openalex.org/W3103479222","https://openalex.org/W3104186312","https://openalex.org/W3105625590","https://openalex.org/W3116637192","https://openalex.org/W3210474121","https://openalex.org/W3213196631","https://openalex.org/W4232150823","https://openalex.org/W4235216760","https://openalex.org/W4251434917","https://openalex.org/W4299805813","https://openalex.org/W4394440700","https://openalex.org/W4394549618","https://openalex.org/W4398315625","https://openalex.org/W4398344212","https://openalex.org/W4398383472","https://openalex.org/W4398575659","https://openalex.org/W4398621682","https://openalex.org/W4398730426","https://openalex.org/W4398835933","https://openalex.org/W4398926523","https://openalex.org/W4398949609","https://openalex.org/W6631217535","https://openalex.org/W6713239141","https://openalex.org/W6743745044","https://openalex.org/W6744059327","https://openalex.org/W6744365282","https://openalex.org/W6744612591","https://openalex.org/W6745977843","https://openalex.org/W6750909162","https://openalex.org/W6752211584","https://openalex.org/W6755371269","https://openalex.org/W6758731303","https://openalex.org/W6772748693","https://openalex.org/W6788071762","https://openalex.org/W6863674722","https://openalex.org/W6863957745","https://openalex.org/W6867593588","https://openalex.org/W6868204271","https://openalex.org/W6868371233","https://openalex.org/W6868377625","https://openalex.org/W6868463160","https://openalex.org/W6868476145","https://openalex.org/W6868485700","https://openalex.org/W6868799611","https://openalex.org/W6868802782","https://openalex.org/W6868822268","https://openalex.org/W6868873829"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516"],"abstract_inverted_index":{"Social":[0],"media":[1],"is":[2,63],"often":[3],"utilized":[4],"as":[5],"a":[6,42,87,145],"lifeline":[7],"for":[8,59,164],"communication":[9],"during":[10],"natural":[11,14,35,116],"disasters.":[12],"Traditionally,":[13],"disaster":[15,36],"tweets":[16],"are":[17],"filtered":[18,39],"f":[19,46],"rom":[20],"t":[21,29,40,129],"he":[22,30],"T":[23],"witter":[24],"s":[25,44],"tream":[26],"u":[27],"sing":[28],"n":[31],"ame":[32],"of":[33,52,77,115],"the":[34,38,106,134,160,165],"and":[37,70,79,121,154],"weets":[41],"re":[43],"ent":[45],"or":[47],"human":[48,53],"annotation.":[49],"The":[50],"process":[51],"annotation":[54],"to":[55,96,110],"create":[56],"labeled":[57],"sets":[58],"machine":[60,102],"learning":[61,103],"models":[62,104,131],"laborious,":[64],"time":[65],"consuming,":[66],"at":[67],"times":[68],"inaccurate,":[69],"more":[71],"importantly":[72],"not":[73],"scalable":[74],"in":[75],"terms":[76],"size":[78],"real-time":[80],"use.":[81],"In":[82,94],"this":[83],"work,":[84],"we":[85,100,158],"curated":[86],"silver":[88,135,161],"standard":[89,136,162],"dataset":[90,137,163],"using":[91],"weak":[92],"supervision.":[93],"order":[95],"validate":[97],"its":[98],"utility,":[99,157],"train":[101],"on":[105,133],"weakly":[107],"supervised":[108],"data":[109],"identify":[111],"three":[112],"different":[113],"types":[114],"disasters":[117],"i.e":[118],"earthquakes,":[119],"hurricanes":[120],"floods.":[122],"O":[123],"ur":[124],"r":[125],"esults":[126],"d":[127],"emonstrate":[128],"hat":[130],"trained":[132],"achieved":[138],"performance":[139],"greater":[140],"than":[141],"90%":[142],"when":[143],"classifying":[144],"manually":[146],"curated,":[147],"gold-standard":[148],"dataset.":[149],"To":[150],"enable":[151],"reproducible":[152],"research":[153],"additional":[155],"downstream":[156],"release":[159],"scientific":[166],"community.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}