{"id":"https://openalex.org/W1523270504","doi":"https://doi.org/10.1109/ccis.2014.7175793","title":"A fast big data collection system using MapReduce framework","display_name":"A fast big data collection system using MapReduce framework","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W1523270504","doi":"https://doi.org/10.1109/ccis.2014.7175793","mag":"1523270504"},"language":"en","primary_location":{"id":"doi:10.1109/ccis.2014.7175793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2014.7175793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems","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/A5100451253","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-2165-2636"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Bing Li","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Kowloon, HK","Department of Computing, The Hong Kong Polytechnic University, , Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Kowloon, HK","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, , Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107049960","display_name":"Keith C. C. Chan","orcid":"https://orcid.org/0000-0001-7962-6564"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Keith C.C. Chan","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong","Department of Computing, The Hong Kong Polytechnic University, , Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, , Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100451253"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.5778,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86777032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"50","issue":null,"first_page":"530","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9944999814033508,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.8640997409820557},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8201438784599304},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6816207766532898},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.554913341999054},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5134207010269165},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.509240984916687},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.485624223947525},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4549834132194519},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.43900078535079956},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4218469560146332},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4170604944229126},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.28320470452308655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24069127440452576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640997409820557},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8201438784599304},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6816207766532898},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.554913341999054},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5134207010269165},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.509240984916687},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.485624223947525},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4549834132194519},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.43900078535079956},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4218469560146332},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4170604944229126},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.28320470452308655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24069127440452576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis.2014.7175793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2014.7175793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1825603816","https://openalex.org/W1989869358","https://openalex.org/W2023210394","https://openalex.org/W2026958591","https://openalex.org/W2067594810","https://openalex.org/W2087572212","https://openalex.org/W2140279085","https://openalex.org/W2164542999","https://openalex.org/W2173213060","https://openalex.org/W2250243742","https://openalex.org/W6638533821","https://openalex.org/W6680536191"],"related_works":["https://openalex.org/W2496086623","https://openalex.org/W2349698472","https://openalex.org/W2279098064","https://openalex.org/W1586511042","https://openalex.org/W2794909838","https://openalex.org/W2967628377","https://openalex.org/W2363068772","https://openalex.org/W1975429881","https://openalex.org/W2551975015","https://openalex.org/W1585941060"],"abstract_inverted_index":{"Social":[0],"network":[1],"like":[2],"a":[3,13,92,105,148,170],"corpus":[4],"with":[5,91,98],"valuable":[6],"data,":[7],"has":[8,41],"attracted":[9],"much":[10,45],"attention":[11],"from":[12,196],"various":[14],"fields":[15],"of":[16,25,35,107,142,157,172,190,194],"researchers":[17],"in":[18,22,46,82],"recent":[19],"years,":[20],"especially":[21],"the":[23,31,33,47,52,55,79,108,133,139,143,154,174,180,188],"subject":[24],"big":[26,80,109],"data":[27,39,53,81,110,195],"analytics.":[28],"However,":[29],"as":[30],"foundation,":[32],"part":[34],"efficient":[36],"and":[37,85,146,161,185],"accurate":[38],"collection":[40,144],"not":[42],"been":[43],"focused":[44],"past":[48],"published":[49],"works.":[50],"During":[51,169],"among":[54],"web":[56,70,89,120,167,198],"increasing":[57],"rapidly,":[58],"this":[59,112],"article":[60,113],"will":[61,114],"identify":[62],"two":[63,100],"major":[64],"challenges":[65,101],"that":[66],"traditional":[67],"distributed":[68],"based":[69,118],"crawler":[71,121],"systems":[72],"cannot":[73],"adapt,":[74],"which":[75,126],"is":[76],"fast":[77],"handling":[78],"social":[83,159],"networks":[84,160],"suiting":[86],"for":[87],"multiple":[88,197],"sources":[90],"uniformed":[93,149],"collecting":[94,162,191],"model.":[95],"To":[96],"deal":[97],"these":[99],"thus":[102,136],"to":[103,130,137,152,164],"build":[104],"foundation":[106],"analytics,":[111],"propose":[115],"an":[116],"Ontology":[117,150],"adapted":[119],"system":[122,177,181],"called":[123],"OACM":[124,176],"system,":[125],"uses":[127],"MapReduce":[128],"model":[129,151],"effectively":[131],"balance":[132],"processing":[134,140],"resources":[135],"fasten":[138],"speed":[141],"procedure":[145],"designs":[147],"estimate":[153],"semantic":[155],"content":[156],"both":[158],"tasks":[163],"adapt":[165],"different":[166],"sources.":[168,199],"set":[171],"experiments,":[173],"proposed":[175],"could":[178,186],"optimize":[179],"resource":[182],"scheduling":[183],"efficiently":[184],"achieve":[187],"task":[189],"large":[192],"amount":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
