{"id":"https://openalex.org/W2295639288","doi":"https://doi.org/10.1145/2567948.2579704","title":"Integrating product data from websites offering microdata markup","display_name":"Integrating product data from websites offering microdata markup","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W2295639288","doi":"https://doi.org/10.1145/2567948.2579704","mag":"2295639288"},"language":"en","primary_location":{"id":"doi:10.1145/2567948.2579704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579704","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":"conference-paper","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/A5018057749","display_name":"Petar Petrovski","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Petar Petrovski","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111326102","display_name":"Volha Bryl","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volha Bryl","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["University of Mannheim, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1299","last_page":"1304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9970999956130981,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.9260596036911011},{"id":"https://openalex.org/keywords/microdata","display_name":"Microdata (statistics)","score":0.8227286338806152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659934759140015},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5856238007545471},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49478787183761597},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4148995578289032},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28930914402008057},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2217615842819214}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.9260596036911011},{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.8227286338806152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659934759140015},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5856238007545471},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49478787183761597},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4148995578289032},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28930914402008057},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2217615842819214},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C52130261","wikidata":"https://www.wikidata.org/wiki/Q39825","display_name":"Census","level":3,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2567948.2579704","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2579704","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"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:36891","is_oa":false,"landing_page_url":"http://ub-madoc.bib.uni-mannheim.de/36891/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3253858714","display_name":null,"funder_award_id":"257943","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W73242358","https://openalex.org/W1583544304","https://openalex.org/W1981590391","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2067566391","https://openalex.org/W2108991785","https://openalex.org/W2123561513","https://openalex.org/W2407521136","https://openalex.org/W3099883947"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3124882577","https://openalex.org/W2045945431","https://openalex.org/W3121353175","https://openalex.org/W4385386698","https://openalex.org/W2035955891","https://openalex.org/W4298259670","https://openalex.org/W3123218450","https://openalex.org/W3144851602","https://openalex.org/W2241782923"],"abstract_inverted_index":{"Large":[0],"numbers":[1,86],"of":[2,24,87,99,102,120],"websites":[3],"have":[4],"started":[5],"to":[6,53,81],"markup":[7,52,60,69],"their":[8,55],"content":[9,20,63],"using":[10,143],"standards":[11],"such":[12,44],"as":[13,40,45,73,75],"Microdata,":[14],"Microformats,":[15],"and":[16,31,48,135],"RDFa.":[17],"The":[18],"marked-up":[19],"elements":[21,64],"comprise":[22],"descriptions":[23,101],"people,":[25],"organizations,":[26],"places,":[27],"events,":[28],"products,":[29],"ratings,":[30],"reviews.":[32],"This":[33,89],"development":[34],"has":[35],"accelerated":[36],"in":[37,96],"last":[38],"years":[39],"major":[41],"search":[42,56],"engines":[43],"Google,":[46],"Bing":[47],"Yahoo!":[49],"use":[50],"the":[51,68,92,97,121,155],"improve":[54],"results.":[57],"Embedding":[58],"semantic":[59],"facilitates":[61],"identifying":[62],"on":[65],"webpages.":[66],"However,":[67],"is":[70],"mostly":[71],"not":[72],"fine-grained":[74],"desirable":[76],"for":[77,117],"applications":[78],"that":[79,94,109],"aim":[80],"integrate":[82],"data":[83,122,136],"from":[84,105,148,154],"large":[85,160],"websites.":[88],"paper":[90],"discusses":[91],"challenges":[93],"arise":[95],"task":[98],"integrating":[100],"electronic":[103],"products":[104],"several":[106],"thousand":[107],"e-shops":[108,150],"offer":[110],"Microdata":[111,126],"markup.":[112],"We":[113,138],"present":[114],"a":[115,159],"solution":[116],"each":[118],"step":[119],"integration":[123],"process":[124],"including":[125],"extraction,":[127,132],"product":[128,130,146],"classification,":[129],"feature":[131],"identity":[133],"resolution,":[134],"fusion.":[137],"evaluate":[139],"our":[140],"processing":[141],"pipeline":[142],"1.9":[144],"million":[145],"offers":[147],"9240":[149],"which":[151],"we":[152],"extracted":[153],"Common":[156],"Crawl":[157],"2012,":[158],"public":[161],"Web":[162],"corpus.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
