{"id":"https://openalex.org/W2578371470","doi":"https://doi.org/10.3233/978-1-61499-672-9-1212","title":"Leveraging Stratification in Twitter Sampling","display_name":"Leveraging Stratification in Twitter Sampling","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2578371470","doi":"https://doi.org/10.3233/978-1-61499-672-9-1212","mag":"2578371470"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-672-9-1212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-672-9-1212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019937451","display_name":"Vikas Joshi","orcid":"https://orcid.org/0000-0003-4467-3621"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Joshi Vikas","raw_affiliation_strings":["IBM Research, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012482178","display_name":"Deepak Padmanabhan","orcid":"https://orcid.org/0000-0002-1336-2356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P Deepak","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science"],"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110205806","display_name":"L. V. Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subramaniam L.V.","raw_affiliation_strings":["IBM Research, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019937451"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33124373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10557","display_name":"Social Media and Politics","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T10557","display_name":"Social Media and Politics","score":0.9958999752998352,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9916999936103821,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9794999957084656,"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/stratification","display_name":"Stratification (seeds)","score":0.6888436079025269},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5023565292358398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45317959785461426},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.3937678933143616},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35717374086380005},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1692238450050354},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08362400531768799}],"concepts":[{"id":"https://openalex.org/C192943249","wikidata":"https://www.wikidata.org/wiki/Q1893382","display_name":"Stratification (seeds)","level":5,"score":0.6888436079025269},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5023565292358398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45317959785461426},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3937678933143616},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35717374086380005},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1692238450050354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08362400531768799},{"id":"https://openalex.org/C100701293","wikidata":"https://www.wikidata.org/wiki/Q193838","display_name":"Germination","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C88548481","wikidata":"https://www.wikidata.org/wiki/Q2397491","display_name":"Seed dormancy","level":4,"score":0.0},{"id":"https://openalex.org/C3527866","wikidata":"https://www.wikidata.org/wiki/Q162267","display_name":"Dormancy","level":3,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-672-9-1212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/edc0084d-0385-46b6-a6a5-22bb31c892af","is_oa":true,"landing_page_url":null,"pdf_url":"https://pureadmin.qub.ac.uk/ws/files/124421739/Leveraging_Stratification_in_Twitter_Sampling.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/edc0084d-0385-46b6-a6a5-22bb31c892af","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/edc0084d-0385-46b6-a6a5-22bb31c892af","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/124421739/Leveraging_Stratification_in_Twitter_Sampling.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Joshi, V, Padmanabhan, D & Subramaniam, LV 2016, Leveraging Stratification in Twitter Sampling. in ECAI 2016. vol. 285, Frontiers in Artificial Intelligence and Applications, IOS Press, pp. 1212-1220, 22nd European Conference on Artificial Intelligence, The Hague, Netherlands, 29/08/2016. https://doi.org/10.3233/978-1-61499-672-9-1212","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-672-9-1212","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-1212","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W185581208","https://openalex.org/W1880262756","https://openalex.org/W1917841893","https://openalex.org/W1996235486","https://openalex.org/W2024937975","https://openalex.org/W2028944004","https://openalex.org/W2029516281","https://openalex.org/W2042587503","https://openalex.org/W2062743812","https://openalex.org/W2180166051","https://openalex.org/W2236011370","https://openalex.org/W2535726973","https://openalex.org/W2949731435","https://openalex.org/W2950350902","https://openalex.org/W3122605581","https://openalex.org/W4231510805","https://openalex.org/W4293859741","https://openalex.org/W6602551176"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4386554877","https://openalex.org/W4236138976","https://openalex.org/W2376932109"],"abstract_inverted_index":{"With":[0],"Tweet":[1],"volumes":[2],"reaching":[3],"500":[4],"million":[5],"a":[6,51],"day,":[7],"sampling":[8],"is":[9,56],"inevitable":[10],"for":[11,99,154],"any":[12],"application":[13],"using":[14,133],"Twitter":[15,123],"data.":[16,124],"Realizing":[17],"this,":[18],"data":[19,29,44,155,180],"providers":[20,156],"such":[21],"as":[22],"Twitter,":[23],"Gnip":[24],"and":[25,135,181],"Boardreader":[26],"license":[27],"sampled":[28,43,164],"streams":[30],"priced":[31],"in":[32,48,91,122],"accordance":[33,92],"with":[34,42,50,93],"the":[35,59,66,83,100,111,139,151,178],"sample":[36,54,88,116],"size.":[37],"Big":[38],"Data":[39],"applications":[40,167],"working":[41,49],"would":[45],"be":[46,79],"interested":[47],"large":[52],"enough":[53],"that":[55,72],"representative":[57],"of":[58,76,102,113,141],"universal":[60],"dataset.":[61],"Previous":[62],"work":[63,149],"focusing":[64],"on":[65,96],"representativeness":[67],"issue":[68],"has":[69],"considered":[70],"ensuring":[71],"global":[73],"occurrence":[74,97],"rates":[75,98],"key":[77],"terms,":[78],"reliably":[80],"estimated":[81],"from":[82],"sample.":[84],"Present":[85],"technology":[86],"allows":[87],"size":[89,117],"estimation":[90],"probabilistic":[94],"bounds":[95],"case":[101],"uniform":[103,145],"random":[104,146],"sampling.":[105,147],"In":[106],"this":[107],"paper,":[108],"we":[109],"consider":[110],"problem":[112],"further":[114],"improving":[115],"estimates":[118,128],"by":[119,170],"leveraging":[120],"stratification":[121],"We":[125],"analyze":[126],"our":[127,142],"through":[129],"an":[130],"extensive":[131],"study":[132],"simulations":[134],"real-world":[136],"data,":[137],"establishing":[138],"superiority":[140],"method":[143],"over":[144],"Our":[148],"provides":[150],"technical":[152],"know-how":[153],"to":[157,161,173],"expand":[158],"their":[159],"portfolio":[160],"include":[162],"stratified":[163],"datasets,":[165],"whereas":[166],"are":[168],"benefited":[169],"being":[171],"able":[172],"monitor":[174],"more":[175],"topics/events":[176],"at":[177],"same":[179],"computing":[182],"cost.":[183]},"counts_by_year":[],"updated_date":"2026-01-01T23:40:50.289205","created_date":"2017-01-26T00:00:00"}