{"id":"https://openalex.org/W2727352725","doi":"https://doi.org/10.1504/ijwgs.2017.10006055","title":"Stream-based live entity resolution approach with adaptive duplicate count strategy","display_name":"Stream-based live entity resolution approach with adaptive duplicate count strategy","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2727352725","doi":"https://doi.org/10.1504/ijwgs.2017.10006055","mag":"2727352725"},"language":"en","primary_location":{"id":"doi:10.1504/ijwgs.2017.10006055","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijwgs.2017.10006055","pdf_url":null,"source":{"id":"https://openalex.org/S200047447","display_name":"International Journal of Web and Grid Services","issn_l":"1741-1106","issn":["1741-1106","1741-1114"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web and Grid Services","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/A5039282629","display_name":"Kun Ma","orcid":"https://orcid.org/0000-0002-0135-5423"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Ma","raw_affiliation_strings":["Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, Shandong, China"],"affiliations":[{"raw_affiliation_string":"Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, Shandong, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065368480","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0001-7961-853X"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yang","raw_affiliation_strings":["Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, Shandong, China"],"affiliations":[{"raw_affiliation_string":"Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, Shandong, China","institution_ids":["https://openalex.org/I34949971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039282629"],"corresponding_institution_ids":["https://openalex.org/I34949971"],"apc_list":null,"apc_paid":null,"fwci":0.775,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75999867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"13","issue":"3","first_page":"351","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9957000017166138,"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/T10862","display_name":"AI in cancer detection","score":0.9517999887466431,"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/computer-science","display_name":"Computer science","score":0.8571154475212097},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.7260429859161377},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6997864246368408},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5364632606506348},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5095065236091614},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5048463940620422},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49208706617355347},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4732140600681305},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.41860291361808777},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34276723861694336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29250866174697876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571154475212097},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.7260429859161377},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6997864246368408},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5364632606506348},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5095065236091614},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5048463940620422},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49208706617355347},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4732140600681305},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.41860291361808777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34276723861694336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29250866174697876},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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:10.1504/ijwgs.2017.10006055","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijwgs.2017.10006055","pdf_url":null,"source":{"id":"https://openalex.org/S200047447","display_name":"International Journal of Web and Grid Services","issn_l":"1741-1106","issn":["1741-1106","1741-1114"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web and Grid Services","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W127192698","https://openalex.org/W2360131081","https://openalex.org/W3014558862","https://openalex.org/W3155969782","https://openalex.org/W3111543298","https://openalex.org/W1970009995","https://openalex.org/W2388307643","https://openalex.org/W2985941356","https://openalex.org/W1572762191","https://openalex.org/W3207785250"],"abstract_inverted_index":{"Recently,":[0],"researchers":[1],"have":[2],"been":[3],"more":[4],"concerned":[5],"about":[6],"large-scale":[7],"news":[8,67,120],"and":[9,68,92,103,129],"tweet":[10,69],"data":[11,23,39,121],"generated":[12],"by":[13,106],"the":[14,22,29,37,41,66,81,119,126,132],"social":[15],"media.":[16],"Some":[17],"cloud":[18,42],"service":[19],"providers":[20],"utilise":[21],"to":[24,35,62,75,83],"find":[25,63,104],"public":[26],"sentiments":[27],"for":[28],"tenants.":[30],"The":[31],"challenge":[32],"is":[33],"how":[34],"clean":[36],"big":[38],"in":[40,80,110],"before":[43],"making":[44],"further":[45],"analysis.":[46],"To":[47],"address":[48,76],"this":[49],"issue,":[50],"we":[51],"propose":[52],"a":[53,60],"new":[54],"live":[55,77],"entity":[56,78],"resolution":[57,79],"approach":[58],"at":[59],"time":[61],"duplicates":[64,105],"from":[65],"data.":[70],"We":[71],"investigate":[72],"possible":[73],"solutions":[74],"cloud,":[82],"make":[84],"sliding":[85],"window":[86,93,101],"size":[87,94],"adaptive":[88],"using":[89],"multistep":[90],"distance":[91],"dependent":[95],"duplicate":[96],"count":[97],"strategy":[98],"with":[99],"alterable":[100],"step,":[102],"overlapping":[107],"boundary":[108],"objects":[109],"adjacent":[111],"blocks.":[112],"Finally,":[113],"our":[114],"experimental":[115],"evaluation":[116],"based":[117],"on":[118,122],"large":[123],"datasets":[124],"shows":[125],"high":[127],"effectiveness":[128],"efficiency":[130],"of":[131],"proposed":[133],"approaches.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
