{"id":"https://openalex.org/W2913268761","doi":"https://doi.org/10.1145/3308558.3313529","title":"RED: Redundancy-Driven Data Extraction from Result Pages?","display_name":"RED: Redundancy-Driven Data Extraction from Result Pages?","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2913268761","doi":"https://doi.org/10.1145/3308558.3313529","mag":"2913268761"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024566364","display_name":"Jinsong Guo","orcid":"https://orcid.org/0000-0002-1142-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinsong Guo","raw_affiliation_strings":["UBS Evidence Lab, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBS Evidence Lab, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["the Department of Engineering, Universita Roma Tre, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the Department of Engineering, Universita Roma Tre, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113511969","display_name":"Tim Furche","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":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["1) the Department of Computer Science, University of Oxford; 2) Wrapidity &amp; Meltwater, United Kingdom","2) Wrapidity & Meltwater, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1) the Department of Computer Science, University of Oxford; 2) Wrapidity &amp; Meltwater, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"2) Wrapidity & Meltwater, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036346128","display_name":"Giovanni Grasso","orcid":"https://orcid.org/0000-0002-4350-0115"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Grasso","raw_affiliation_strings":["1) the Department of Mathematics and Computer Science, University of Calabria; 2) Wrapidity &amp; Meltwater, Italy","2) Wrapidity & Meltwater, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1) the Department of Mathematics and Computer Science, University of Calabria; 2) Wrapidity &amp; Meltwater, Italy","institution_ids":["https://openalex.org/I45204951"]},{"raw_affiliation_string":"2) Wrapidity & Meltwater, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050151740","display_name":"Georg Gottlob","orcid":"https://orcid.org/0000-0002-2353-5230"},"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":false,"raw_author_name":"Georg Gottlob","raw_affiliation_strings":["1) the Department of Computer Science, University of Oxford; 2) the Faculty of Informatics, TU Wien, United Kingdom","1) the Department of Computer Science, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1) the Department of Computer Science, University of Oxford; 2) the Faculty of Informatics, TU Wien, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"1) the Department of Computer Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11719","display_name":"Data Quality and Management","score":0.9663000106811523,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9567000269889832,"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":0.8008002042770386},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7261751890182495},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.6860741376876831},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5784107446670532},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5467967391014099},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.44658759236335754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43764254450798035},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3457135558128357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24020463228225708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008002042770386},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7261751890182495},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.6860741376876831},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5784107446670532},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5467967391014099},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.44658759236335754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43764254450798035},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3457135558128357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24020463228225708},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3308558.3313529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/372507","is_oa":true,"landing_page_url":"http://hdl.handle.net/11590/372507","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:081daa4a-01f9-430d-8d04-bf35226d72c2","is_oa":true,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:081daa4a-01f9-430d-8d04-bf35226d72c2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313529","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313529","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3878900231","display_name":null,"funder_award_id":"EP/M025268/1 VADA","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5458651130","display_name":null,"funder_award_id":"M025268","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8298339663","display_name":"VADA: Value Added Data Systems -- Principles and Architecture","funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8891597062","display_name":null,"funder_award_id":"EP/M025268/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W939911738","https://openalex.org/W1494141893","https://openalex.org/W1534024124","https://openalex.org/W1601949013","https://openalex.org/W1646278814","https://openalex.org/W1971415141","https://openalex.org/W1999778371","https://openalex.org/W2001104490","https://openalex.org/W2002956097","https://openalex.org/W2011539648","https://openalex.org/W2013469079","https://openalex.org/W2013970953","https://openalex.org/W2015551056","https://openalex.org/W2038231646","https://openalex.org/W2040757233","https://openalex.org/W2069388662","https://openalex.org/W2080132606","https://openalex.org/W2096496923","https://openalex.org/W2097874932","https://openalex.org/W2100164132","https://openalex.org/W2101654853","https://openalex.org/W2120170839","https://openalex.org/W2123853152","https://openalex.org/W2134172329","https://openalex.org/W2145941243","https://openalex.org/W2148317291","https://openalex.org/W2148579753","https://openalex.org/W2148738951","https://openalex.org/W2150721933","https://openalex.org/W2152956989","https://openalex.org/W2154444297","https://openalex.org/W2160189941","https://openalex.org/W2168358004","https://openalex.org/W2170971772","https://openalex.org/W2216972693","https://openalex.org/W2296164608","https://openalex.org/W2326804586","https://openalex.org/W2405968456","https://openalex.org/W2421306863","https://openalex.org/W2788315304","https://openalex.org/W4249682906","https://openalex.org/W4253933599","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2294677930","https://openalex.org/W2801905285","https://openalex.org/W2028846973","https://openalex.org/W2698935035","https://openalex.org/W2756635080","https://openalex.org/W249766449","https://openalex.org/W1504443673","https://openalex.org/W2230419033","https://openalex.org/W2086821603","https://openalex.org/W2354149895"],"abstract_inverted_index":{"Data-driven":[0],"websites":[1],"are":[2],"mostly":[3],"accessed":[4],"through":[5],"search":[6,31],"interfaces.":[7],"Such":[8],"sites":[9],"follow":[10],"a":[11,30,35,55],"common":[12],"publishing":[13],"pattern":[14],"that,":[15],"surprisingly,":[16],"has":[17],"not":[18],"been":[19],"fully":[20],"exploited":[21],"for":[22],"unsupervised":[23],"data":[24],"extraction":[25],"yet:":[26],"the":[27,45,59],"result":[28,39,42],"of":[29,38,61],"is":[32],"presented":[33],"as":[34],"paginated":[36],"list":[37],"records.":[40],"Each":[41],"record":[43],"contains":[44],"main":[46],"attributes":[47],"about":[48],"one":[49],"single":[50],"object,":[51],"and":[52],"links":[53],"to":[54,58],"page":[56],"dedicated":[57],"details":[60],"that":[62],"object.":[63]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
