{"id":"https://openalex.org/W4232736084","doi":"https://doi.org/10.1109/glocom.2014.7416974","title":"The Impact of Sampling on Big Data Analysis of Social Media: A Case Study on Flu and Ebola","display_name":"The Impact of Sampling on Big Data Analysis of Social Media: A Case Study on Flu and Ebola","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W4232736084","doi":"https://doi.org/10.1109/glocom.2014.7416974"},"language":"en","primary_location":{"id":"doi:10.1109/glocom.2014.7416974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/glocom.2014.7416974","pdf_url":null,"source":{"id":"https://openalex.org/S4363607712","display_name":"2015 IEEE Global Communications Conference (GLOBECOM)","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":"2015 IEEE Global Communications Conference (GLOBECOM)","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/A5049423626","display_name":"Kuai Xu","orcid":"https://orcid.org/0000-0001-6659-6773"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuai Xu","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431362","display_name":"Feng Wang","orcid":"https://orcid.org/0000-0003-1427-5964"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013643572","display_name":"Xiaohua Jia","orcid":"https://orcid.org/0000-0001-8702-8302"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaohua Jia","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091211890","display_name":"Haiyan Wang","orcid":"https://orcid.org/0000-0002-5204-967X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyan Wang","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3231,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56578947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7276903986930847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7240812182426453},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.6832622289657593},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.6196472644805908},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6142880320549011},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6069155335426331},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5699162483215332},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.5340180993080139},{"id":"https://openalex.org/keywords/sampling-design","display_name":"Sampling design","score":0.42135509848594666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4043395519256592},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2942981719970703},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28641730546951294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1492069959640503}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7276903986930847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240812182426453},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.6832622289657593},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.6196472644805908},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6142880320549011},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6069155335426331},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5699162483215332},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.5340180993080139},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.42135509848594666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4043395519256592},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2942981719970703},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28641730546951294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1492069959640503},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/glocom.2014.7416974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/glocom.2014.7416974","pdf_url":null,"source":{"id":"https://openalex.org/S4363607712","display_name":"2015 IEEE Global Communications Conference (GLOBECOM)","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":"2015 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W49973572","https://openalex.org/W1566772816","https://openalex.org/W1845748792","https://openalex.org/W2004671457","https://openalex.org/W2052618365","https://openalex.org/W2062743812","https://openalex.org/W2096745865","https://openalex.org/W2099111195","https://openalex.org/W2101196063","https://openalex.org/W2112405643","https://openalex.org/W2115022330","https://openalex.org/W2117192789","https://openalex.org/W2117410972","https://openalex.org/W2137135938","https://openalex.org/W6638777778"],"related_works":["https://openalex.org/W2350399852","https://openalex.org/W4238714840","https://openalex.org/W2555206834","https://openalex.org/W225930446","https://openalex.org/W3047864323","https://openalex.org/W4233896666","https://openalex.org/W2383809451","https://openalex.org/W2322994712","https://openalex.org/W2056178673","https://openalex.org/W4225149851"],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"of":[3,14,29,44,67,73,106,109,132],"online":[4,57,74,110],"social":[5,19,58,75,111],"networks":[6,76],"in":[7,16,56],"recent":[8],"years":[9],"have":[10],"generated":[11],"massive":[12],"amount":[13],"data-sets":[15,46],"user":[17],"behaviors,":[18],"graphs,":[20,134],"and":[21,27,37,50,54,95,98,129,143],"contents.":[22],"Given":[23],"the":[24,42,45,65,71,121,130,137],"scale,":[25],"heterogeneity,":[26],"diversity":[28],"such":[30],"big":[31],"data,":[32],"sampling":[33,69,90,94,119],"becomes":[34],"a":[35,82,103],"simple":[36],"intuitive":[38],"approach":[39],"to":[40],"reduce":[41],"size":[43],"for":[47],"collecting,":[48],"measuring,":[49],"understanding":[51],"users,":[52],"behaviors":[53],"traffic":[55],"networks.":[59,112],"In":[60,85],"this":[61],"paper,":[62],"we":[63,87],"quantify":[64],"impact":[66,101,123],"random":[68,142],"on":[70,102,124],"analysis":[72],"with":[77],"Twitter":[78],"streaming":[79],"data":[80,139],"as":[81,141],"case":[83],"study.":[84],"addition,":[86],"design":[88],"different":[89],"strategies":[91],"including":[92],"community":[93,118],"strata":[96],"sampling,":[97],"evaluate":[99],"their":[100],"broad":[104],"range":[105],"behavioral":[107],"characteristics":[108],"Our":[113],"experimental":[114],"results":[115],"show":[116],"that":[117],"has":[120],"minimum":[122],"tweet":[125],"distributions":[126],"across":[127],"users":[128],"structure":[131],"retweeting":[133],"while":[135],"achieving":[136],"similar":[138],"reductions":[140],"stratified":[144],"sampling.":[145]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}