{"id":"https://openalex.org/W4234307579","doi":"https://doi.org/10.1109/jcdl.2014.6970160","title":"Crowd-sourcing Web knowledge for metadata extraction","display_name":"Crowd-sourcing Web knowledge for metadata extraction","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W4234307579","doi":"https://doi.org/10.1109/jcdl.2014.6970160"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2014.6970160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","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/A5101973484","display_name":"Zhaohui Wu","orcid":"https://orcid.org/0000-0002-4319-3645"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhaohui Wu","raw_affiliation_strings":["Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069048388","display_name":"Wenyi Huang","orcid":"https://orcid.org/0000-0002-3526-6314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyi Huang","raw_affiliation_strings":["Information Sciences and Technology, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, University Park, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053537544","display_name":"Chen Liang","orcid":"https://orcid.org/0000-0002-0124-4133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Information Sciences and Technology, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, University Park, PA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101973484"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78665716,"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":"141","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/metadata","display_name":"Metadata","score":0.8566724061965942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231882452964783},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.8085465431213379},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5814592838287354},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.49613651633262634},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48358672857284546},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45701009035110474},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4129568934440613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06744828820228577}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8566724061965942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231882452964783},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.8085465431213379},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5814592838287354},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.49613651633262634},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48358672857284546},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45701009035110474},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4129568934440613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06744828820228577},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2014.6970160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","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":14,"referenced_works":["https://openalex.org/W120286951","https://openalex.org/W1693085440","https://openalex.org/W1995470018","https://openalex.org/W2067760738","https://openalex.org/W2102162869","https://openalex.org/W2153635508","https://openalex.org/W2155160033","https://openalex.org/W2181558882","https://openalex.org/W2294688454","https://openalex.org/W2951911250","https://openalex.org/W6604900475","https://openalex.org/W6675206559","https://openalex.org/W6685936606","https://openalex.org/W6697143862"],"related_works":["https://openalex.org/W1950598572","https://openalex.org/W1552553528","https://openalex.org/W2183628870","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2782431616","https://openalex.org/W2394393789","https://openalex.org/W2374379029","https://openalex.org/W1503116306","https://openalex.org/W4299935056"],"abstract_inverted_index":{"We":[0,46],"explore":[1],"a":[2,48],"new":[3,18],"metadata":[4,55],"extraction":[5],"framework":[6],"without":[7],"human":[8],"annotators":[9],"with":[10,53],"the":[11,27,32],"ground":[12],"truth":[13],"harvested":[14],"from":[15],"Web.":[16],"A":[17],"training":[19],"sample":[20],"is":[21],"selected":[22],"based":[23],"on":[24,37],"not":[25],"only":[26],"uncertainty":[28],"and":[29,40,56,72],"representativeness":[30],"in":[31,42],"unlabeled":[33],"pool,":[34],"but":[35],"also":[36],"its":[38,70],"availability":[39],"credibility":[41],"Web":[43,62],"knowledge":[44],"bases.":[45],"construct":[47],"dataset":[49],"of":[50],"4329":[51],"books":[52],"valid":[54],"evaluate":[57],"our":[58],"approach":[59],"using":[60],"5":[61],"book":[63],"databases":[64],"as":[65],"oracles.":[66],"Empirical":[67],"results":[68],"demonstrate":[69],"effectiveness":[71],"efficiency.":[73]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
