{"id":"https://openalex.org/W2741544939","doi":"https://doi.org/10.1145/3077136.3080667","title":"Finally, a Downloadable Test Collection of Tweets","display_name":"Finally, a Downloadable Test Collection of Tweets","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741544939","doi":"https://doi.org/10.1145/3077136.3080667","mag":"2741544939"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3080667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079868963","display_name":"Royal Sequiera","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Royal Sequiera","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.8305,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.77902792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1225","last_page":"1228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057658076286316},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.6604119539260864},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6537074446678162},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6068812012672424},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5754148960113525},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.5319141745567322},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.516980767250061},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5065046548843384},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3880578279495239},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3226741850376129},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20122641324996948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057658076286316},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.6604119539260864},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6537074446678162},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6068812012672424},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5754148960113525},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.5319141745567322},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.516980767250061},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5065046548843384},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3880578279495239},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3226741850376129},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20122641324996948},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3080667","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1989220366","https://openalex.org/W2000431947","https://openalex.org/W2066682493","https://openalex.org/W2083604559","https://openalex.org/W2112438052","https://openalex.org/W2271209846","https://openalex.org/W2339562433","https://openalex.org/W2396476612","https://openalex.org/W2515979697"],"related_works":["https://openalex.org/W2183842793","https://openalex.org/W2053241453","https://openalex.org/W2017590198","https://openalex.org/W2275433313","https://openalex.org/W2978974359","https://openalex.org/W2153980712","https://openalex.org/W2087532526","https://openalex.org/W2728430307","https://openalex.org/W1805578373","https://openalex.org/W2107786128"],"abstract_inverted_index":{"Due":[0],"to":[1,48,70,87,96,152],"Twitter's":[2],"terms":[3,145],"of":[4,9,15,38,116,146,179,189],"service":[5],"that":[6,41,67,103,154],"forbid":[7],"redistribution":[8],"content,":[10],"creating":[11],"publicly":[12],"downloadable":[13,177],"collections":[14,30,71],"tweets":[16,40],"for":[17,25,72,112,165],"research":[18,27,172],"purposes":[19],"has":[20,55,95,108],"been":[21,109],"a":[22,82,162,176],"perpetual":[23],"problem":[24],"the":[26,36,39,43,50,77,90,98,104,117,124,128,133,155,166,171,187,198],"community.":[28],"Some":[29],"are":[31],"distributed":[32],"by":[33],"making":[34,110],"available":[35,111],"ids":[37],"comprise":[42],"collection":[44,130,178],"and":[45,136,149,194],"providing":[46,170],"tools":[47],"fetch":[49],"actual":[51],"content;":[52],"this":[53,182],"approach":[54],"scalability":[56],"limitations.":[57],"In":[58],"other":[59],"cases,":[60],"evaluation":[61],"organizers":[62],"have":[63,101],"set":[64],"up":[65],"APIs":[66],"provide":[68],"access":[69],"specific":[73],"tasks,":[74],"without":[75],"exposing":[76],"underlying":[78],"content.":[79],"This":[80],"is":[81,123],"workable":[83],"solution,":[84],"but":[85],"difficult":[86],"sustain":[88],"over":[89,192],"long":[91],"term":[92],"since":[93],"someone":[94],"maintain":[97],"APIs.":[99],"We":[100,140],"noticed":[102],"non-profit":[105],"Internet":[106,156],"Archive":[107,157],"public":[113],"download":[114],"captures":[115],"so-called":[118],"Twitter":[119],"\"spritzer\"":[120],"stream,":[121],"which":[122],"same":[125],"source":[126],"as":[127,161],"Tweets2013":[129,167],"used":[131],"in":[132,144],"TREC":[134],"2013":[135],"2014":[137],"Microblog":[138],"Tracks.":[139],"analyzed":[141],"both":[142],"datasets":[143],"content":[147],"overlap":[148],"retrieval":[150],"baselines":[151],"show":[153],"data":[158],"can":[159],"serve":[160],"drop-in":[163],"replacement":[164],"collection,":[168],"thereby":[169],"community":[173],"with,":[174],"finally,":[175],"tweets.":[180],"Beyond":[181],"finding,":[183],"we":[184],"also":[185],"study":[186],"impact":[188],"tweet":[190],"deletions":[191],"time":[193],"how":[195],"they":[196],"affect":[197],"test":[199],"collections.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
