{"id":"https://openalex.org/W2289661175","doi":"https://doi.org/10.1145/2567948.2579708","title":"An analysis of duplicate on web extracted objects","display_name":"An analysis of duplicate on web extracted objects","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W2289661175","doi":"https://doi.org/10.1145/2567948.2579708","mag":"2289661175"},"language":"en","primary_location":{"id":"doi:10.1145/2567948.2579708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on World Wide Web","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/A5057963374","display_name":"Stefano Ortona","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stefano Ortona","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057963374"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.4058,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72278526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1279","last_page":"1284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9853000044822693,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.678318202495575},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3826894462108612},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3585340082645416},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3434542119503021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678318202495575},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3826894462108612},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3585340082645416},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3434542119503021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2567948.2579708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W149565845","https://openalex.org/W1610496399","https://openalex.org/W1646278814","https://openalex.org/W1971415141","https://openalex.org/W1981590391","https://openalex.org/W1986017822","https://openalex.org/W1992673035","https://openalex.org/W1997927541","https://openalex.org/W1999823970","https://openalex.org/W2024105308","https://openalex.org/W2031250218","https://openalex.org/W2034190452","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2056748234","https://openalex.org/W2065758089","https://openalex.org/W2080132606","https://openalex.org/W2081186682","https://openalex.org/W2083413555","https://openalex.org/W2097002571","https://openalex.org/W2097874932","https://openalex.org/W2106895292","https://openalex.org/W2107499437","https://openalex.org/W2108991785","https://openalex.org/W2114764731","https://openalex.org/W2117312440","https://openalex.org/W2147805208","https://openalex.org/W2151763080","https://openalex.org/W2168320385","https://openalex.org/W6605982101","https://openalex.org/W6635176900","https://openalex.org/W6636177537","https://openalex.org/W6670527621","https://openalex.org/W6677336291"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Today":[0],"the":[1,5,30,33,39,53,72,84,95,104],"web":[2,18,41,85,92],"has":[3,24,66],"become":[4],"largest":[6],"available":[7],"source":[8],"of":[9,14,35,68,97],"information.":[10],"The":[11],"automatic":[12],"extraction":[13,31],"structured":[15],"data":[16,51],"from":[17,103],"is":[19],"a":[20],"challenging":[21],"problem":[22,34,82,96],"that":[23],"been":[25,67],"widely":[26],"investigated.":[27],"However,":[28],"after":[29],"process,":[32],"identifying":[36,98],"duplicates":[37,99],"among":[38,100],"extracted":[40,102],"records":[42,101],"must":[43],"be":[44],"solved":[45],"in":[46,83],"order":[47],"to":[48,52],"present":[49,91],"clean":[50],"final":[54],"user.":[55],"This":[56],"problem,":[57],"also":[58],"known":[59],"as":[60],"record":[61,64],"linkage":[62],"or":[63],"matching,":[65,94],"central":[69],"interest":[70],"for":[71],"database":[73],"community;":[74],"however,":[75],"only":[76],"few":[77],"works":[78],"have":[79],"addressed":[80],"this":[81,88],"context.":[86],"In":[87],"paper":[89],"we":[90],"object":[93],"web.":[105]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}