{"id":"https://openalex.org/W3008292886","doi":"https://doi.org/10.1109/tcss.2020.2970602","title":"Mitigating the Impact of Data Sampling on Social Media Analysis and Mining","display_name":"Mitigating the Impact of Data Sampling on Social Media Analysis and Mining","publication_year":2020,"publication_date":"2020-02-18","ids":{"openalex":"https://openalex.org/W3008292886","doi":"https://doi.org/10.1109/tcss.2020.2970602","mag":"3008292886"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2020.2970602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2020.2970602","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","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/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":["School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA"],"raw_orcid":"https://orcid.org/0000-0001-6659-6773","affiliations":[{"raw_affiliation_string":"School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA","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":["School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA"],"raw_orcid":"https://orcid.org/0000-0003-1427-5964","affiliations":[{"raw_affiliation_string":"School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","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":["School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical and Natural Sciences, Arizona State University, Glendale, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773253","display_name":"Yufang Wang","orcid":"https://orcid.org/0000-0001-7725-4533"},"institutions":[{"id":"https://openalex.org/I193524592","display_name":"Tianjin University of Finance and Economics","ror":"https://ror.org/05ev1jb90","country_code":"CN","type":"education","lineage":["https://openalex.org/I193524592"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufang Wang","raw_affiliation_strings":["Tianjin University of Finance and Economics, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-7725-4533","affiliations":[{"raw_affiliation_string":"Tianjin University of Finance and Economics, Tianjin, China","institution_ids":["https://openalex.org/I193524592"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["University of Technology Sydney, Ultimo, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2674-1638","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Ultimo, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6027,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.82834351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"2","first_page":"546","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9973999857902527,"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":0.9973999857902527,"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/T11478","display_name":"Caching and Content Delivery","score":0.9957000017166138,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9940000176429749,"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/social-media","display_name":"Social media","score":0.7412012219429016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7334591150283813},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6376118659973145},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6227060556411743},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49621397256851196},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.46781206130981445},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4228099584579468},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2940221428871155},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.25895631313323975}],"concepts":[{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7412012219429016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334591150283813},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6376118659973145},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6227060556411743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49621397256851196},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.46781206130981445},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4228099584579468},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2940221428871155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25895631313323975}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcss.2020.2970602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2020.2970602","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/143701","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/143701","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.6700000166893005,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3817945477","display_name":null,"funder_award_id":"ATD-1737861","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8578351405","display_name":null,"funder_award_id":"19JCQNJC14800","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"}],"funders":[{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W49973572","https://openalex.org/W1614298861","https://openalex.org/W1845748792","https://openalex.org/W1880262756","https://openalex.org/W2008503861","https://openalex.org/W2008607062","https://openalex.org/W2020754036","https://openalex.org/W2033389579","https://openalex.org/W2055076627","https://openalex.org/W2090658088","https://openalex.org/W2110676972","https://openalex.org/W2112405643","https://openalex.org/W2130324521","https://openalex.org/W2132069633","https://openalex.org/W2146168695","https://openalex.org/W2147717514","https://openalex.org/W2160167256","https://openalex.org/W2165874743","https://openalex.org/W2236011370","https://openalex.org/W2242576003","https://openalex.org/W2244033198","https://openalex.org/W2291804097","https://openalex.org/W2293159451","https://openalex.org/W2542459869","https://openalex.org/W2595177560","https://openalex.org/W2783939666","https://openalex.org/W2786499150","https://openalex.org/W2789679840","https://openalex.org/W2828486017","https://openalex.org/W2913854892","https://openalex.org/W2963750715","https://openalex.org/W4285719527","https://openalex.org/W4300601563","https://openalex.org/W6636510571","https://openalex.org/W6639619044","https://openalex.org/W6679026858","https://openalex.org/W6679663036","https://openalex.org/W6684578312","https://openalex.org/W6689774210"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W4389543811","https://openalex.org/W2122605835"],"abstract_inverted_index":{"The":[0],"last":[1],"decade":[2],"has":[3,32],"witnessed":[4],"the":[5,18,22,26,70,77,103,109,121,153,185,192,199,206,214,226],"explosive":[6],"growth":[7],"of":[8,25,86,98,112,120,124,135,155,195,208,228],"online":[9,87],"social":[10,28,30,57,88,158,232],"media":[11,31,58,159,233],"in":[12,126,162],"users":[13],"and":[14,21,43,73,83,115,147,168,189,224,235],"contents.":[15],"Due":[16],"to":[17,69,107,151,182,217,222],"unprecedented":[19],"scale":[20],"cascading":[23,193],"power":[24],"underlying":[27],"networks,":[29],"created":[33],"a":[34,95,133,219],"new":[35],"paradigm":[36],"for":[37],"sharing":[38],"information,":[39],"broadcasting":[40],"breaking":[41],"news,":[42],"reporting":[44],"real-time":[45,186],"events":[46,167,188,197],"by":[47,66],"any":[48,53],"user":[49],"from":[50,198],"anywhere":[51],"at":[52],"time.":[54],"Many":[55],"popular":[56],"sites":[59,91],"including":[60],"Twitter":[61,127,202],"provide":[62],"streaming":[63,99],"data":[64,79,105,128,160,203,229],"services":[65],"standard":[67],"APIs":[68],"broad":[71],"researcher":[72],"developer":[74],"communities.":[75],"Given":[76],"sheer":[78],"volume,":[80],"rapid":[81],"velocity,":[82],"feature":[84],"variety":[85],"media,":[89],"these":[90,196],"often":[92],"supply":[93],"only":[94],"sampled":[96,201],"set":[97,106],"data,":[100],"rather":[101],"than":[102],"full":[104],"reduce":[108],"resource":[110],"cost":[111],"computations,":[113],"storage,":[114],"network":[116],"bandwidth.":[117],"In":[118],"light":[119],"substantial":[122],"impact":[123,154,227],"sampling":[125,156,230],"stream,":[129],"this":[130,211],"article":[131,212],"explores":[132],"combination":[134],"spectral":[136],"clustering,":[137],"locality-sensitive":[138],"hashing":[139],"(LSH),":[140],"latent":[141],"Dirichlet":[142],"allocation":[143],"(LDA)":[144],"topic":[145],"modeling,":[146],"differential":[148],"equation":[149],"modeling":[150],"mitigate":[152,225],"on":[157,164,231],"analysis,":[161],"particular":[163],"detecting":[165],"real-world":[166],"predicting":[169],"information":[170],"diffusion.":[171],"Our":[172],"extensive":[173],"experiments":[174],"demonstrate":[175],"that":[176],"our":[177,209],"proposed":[178],"method":[179],"is":[180,213],"able":[181],"detect":[183],"effectively":[184],"emerging":[187],"predict":[190],"accurately":[191],"pattern":[194],"1%":[200],"stream.":[204],"To":[205],"best":[207],"knowledge,":[210],"first":[215],"effort":[216],"introduce":[218],"systematic":[220],"methodology":[221],"study":[223],"analysis":[234],"mining.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}