{"id":"https://openalex.org/W2244033198","doi":"https://doi.org/10.1145/2746366","title":"Should We Use the Sample? Analyzing Datasets Sampled from Twitter\u2019s Stream API","display_name":"Should We Use the Sample? Analyzing Datasets Sampled from Twitter\u2019s Stream API","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2244033198","doi":"https://doi.org/10.1145/2746366","mag":"2244033198"},"language":"en","primary_location":{"id":"doi:10.1145/2746366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746366","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-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/A5102914991","display_name":"Yazhe Wang","orcid":"https://orcid.org/0000-0002-1709-5283"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yazhe Wang","raw_affiliation_strings":["Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009879041","display_name":"Jamie Callan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamie Callan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050328715","display_name":"Baihua Zheng","orcid":"https://orcid.org/0000-0001-9792-9171"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Baihua Zheng","raw_affiliation_strings":["Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102914991"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":2.607,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.89669592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"9","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/microblogging","display_name":"Microblogging","score":0.8736081719398499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717729806900024},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.762423038482666},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6676009297370911},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6268720030784607},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5309545397758484},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48482027649879456},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.42476171255111694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08708196878433228}],"concepts":[{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.8736081719398499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717729806900024},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.762423038482666},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6676009297370911},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6268720030784607},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5309545397758484},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48482027649879456},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.42476171255111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08708196878433228},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2746366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746366","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-3866","is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3866&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/2746366","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G780389946","display_name":null,"funder_award_id":"NSF IIS-1160862","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320328656","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W7530263","https://openalex.org/W49973572","https://openalex.org/W1517590677","https://openalex.org/W1526460642","https://openalex.org/W1845748792","https://openalex.org/W1965936846","https://openalex.org/W1967579779","https://openalex.org/W1986697120","https://openalex.org/W1986828474","https://openalex.org/W1988183975","https://openalex.org/W2000200507","https://openalex.org/W2010273307","https://openalex.org/W2018165284","https://openalex.org/W2028897509","https://openalex.org/W2033995706","https://openalex.org/W2042901984","https://openalex.org/W2046804949","https://openalex.org/W2060009247","https://openalex.org/W2062743812","https://openalex.org/W2101196063","https://openalex.org/W2115022330","https://openalex.org/W2116204558","https://openalex.org/W2117410972","https://openalex.org/W2118519969","https://openalex.org/W2121761994","https://openalex.org/W2122710250","https://openalex.org/W2124499489","https://openalex.org/W2131492273","https://openalex.org/W2134746982","https://openalex.org/W2139575250","https://openalex.org/W2146008005","https://openalex.org/W2149510050","https://openalex.org/W2150797113","https://openalex.org/W2168332560","https://openalex.org/W2171468534","https://openalex.org/W2290683883","https://openalex.org/W3122139608","https://openalex.org/W4285719527","https://openalex.org/W6657941742"],"related_works":["https://openalex.org/W2728430307","https://openalex.org/W2107786128","https://openalex.org/W2053241453","https://openalex.org/W2153980712","https://openalex.org/W2537388533","https://openalex.org/W2978974359","https://openalex.org/W2021183651","https://openalex.org/W2036556872","https://openalex.org/W2017590198","https://openalex.org/W2353191283"],"abstract_inverted_index":{"Researchers":[0],"have":[1,72],"begun":[2],"studying":[3],"content":[4],"obtained":[5,110],"from":[6,111],"microblogging":[7],"services":[8],"such":[9],"as":[10],"Twitter":[11,27,64,96,121,132],"to":[12,39,86,123],"address":[13],"a":[14,43,105,118],"variety":[15],"of":[16,26,33,46,63,95,113,128,131],"technological,":[17],"social,":[18],"and":[19,29,41,51,77,135],"commercial":[20,53],"research":[21,50],"questions.":[22],"The":[23],"large":[24],"number":[25],"users":[28],"even":[30],"larger":[31],"volume":[32],"tweets":[34],"often":[35,59],"make":[36],"it":[37],"impractical":[38],"collect":[40],"maintain":[42],"complete":[44,120],"record":[45],"activity;":[47],"therefore,":[48],"most":[49,68],"some":[52],"software":[54],"applications":[55],"rely":[56],"on":[57,75,108],"samples,":[58,62],"relatively":[60],"small":[61],"data.":[65,97],"For":[66],"the":[67,92,129],"part,":[69],"sample":[70],"sizes":[71],"been":[73,84],"based":[74],"availability":[76],"practical":[78],"considerations.":[79],"Relatively":[80],"little":[81],"attention":[82],"has":[83],"paid":[85],"how":[87],"well":[88],"these":[89],"samples":[90,109,134],"represent":[91],"underlying":[93],"stream":[94],"To":[98],"fill":[99],"this":[100,102],"gap,":[101],"article":[103],"performs":[104],"comparative":[106],"analysis":[107],"two":[112],"Twitter\u2019s":[114],"streaming":[115],"APIs":[116],"with":[117],"more":[119],"dataset":[122],"gain":[124],"an":[125],"in-depth":[126],"understanding":[127],"nature":[130],"data":[133,142],"their":[136],"potential":[137],"for":[138],"use":[139],"in":[140],"various":[141],"mining":[143],"tasks.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}