{"id":"https://openalex.org/W1686057074","doi":"https://doi.org/10.1109/icde.2004.1320065","title":"Mining the Web for generating thematic metadata from textual data","display_name":"Mining the Web for generating thematic metadata from textual data","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W1686057074","doi":"https://doi.org/10.1109/icde.2004.1320065","mag":"1686057074"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2004.1320065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","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/A5001969602","display_name":"Chien\u2010Chung Huang","orcid":"https://orcid.org/0000-0003-3482-2646"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chien-Chung Huang","raw_affiliation_strings":["Academia Sinica, Taiwan","Acad. Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Acad. Sinica, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022191055","display_name":"Shui\u2010Lung Chuang","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shui-Lung Chuang","raw_affiliation_strings":["Academia Sinica, Taiwan","Acad. Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Acad. Sinica, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085932325","display_name":"Lee\u2010Feng Chien","orcid":"https://orcid.org/0000-0001-9870-2905"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lee-Feng Chien","raw_affiliation_strings":["Academia Sinica, Taiwan","Acad. Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Acad. Sinica, Taipei, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001969602"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.07840431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"834","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","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":0.9980000257492065,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9930999875068665,"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":0.8837003111839294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8545845746994019},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7669631242752075},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.606604278087616},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.526377260684967},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.5200785994529724},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4781440496444702},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4663955569267273},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4472188651561737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22343364357948303}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8837003111839294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8545845746994019},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7669631242752075},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.606604278087616},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.526377260684967},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.5200785994529724},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4781440496444702},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4663955569267273},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4472188651561737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22343364357948303},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2004.1320065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2004.1320065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 20th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.117.1518","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.117.1518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csdl.computer.org/comp/proceedings/icde/2004/2065/00/20650834.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1497212108","https://openalex.org/W1540931780","https://openalex.org/W1633771733","https://openalex.org/W1978329176","https://openalex.org/W1978394996","https://openalex.org/W1979495886","https://openalex.org/W2034953016","https://openalex.org/W2064538096","https://openalex.org/W2102809600","https://openalex.org/W2137096228","https://openalex.org/W2157963512"],"related_works":["https://openalex.org/W3021038098","https://openalex.org/W1552553528","https://openalex.org/W2497487026","https://openalex.org/W2183628870","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2379265733","https://openalex.org/W2394393789","https://openalex.org/W2374379029","https://openalex.org/W1503116306"],"abstract_inverted_index":{"Conventional":[0],"tools":[1],"for":[2,37],"automatic":[3],"metadata":[4,52],"creation":[5],"mostly":[6],"extract":[7],"named":[8],"entities":[9],"or":[10],"patterns":[11],"from":[12],"texts":[13],"and":[14,23,68,89,107],"annotate":[15],"them":[16],"with":[17,53],"information":[18,32],"about":[19],"persons,":[20],"locations,":[21],"dates,":[22],"so":[24],"on.":[25],"However,":[26],"this":[27],"kind":[28],"of":[29,79,100],"entity":[30],"type":[31],"is":[33,63],"often":[34],"too":[35],"primitive":[36],"more":[38],"advanced":[39],"intelligent":[40],"applications":[41],"such":[42],"as":[43],"concept-based":[44],"search.":[45],"Here,":[46],"we":[47],"try":[48],"to":[49,64,71,103,115],"generate":[50],"semantically-deep":[51],"limited":[54],"human":[55],"intervention.":[56],"The":[57,75,93],"main":[58],"idea":[59],"behind":[60],"our":[61],"approach":[62],"use":[65],"Web":[66,104],"mining":[67],"categorization":[69],"techniques":[70],"create":[72],"thematic":[73],"metadata.":[74],"proposed":[76],"approach,":[77],"comprises":[78],"three":[80],"computational":[81],"modules:":[82],"feature":[83,94],"extraction,":[84],"HCQF":[85],"(hier-concept":[86],"query":[87],"formulation)":[88],"text":[90,101],"instance":[91],"categorization.":[92],"extraction":[95],"module":[96],"sends":[97],"the":[98,108],"name":[99],"instances":[102],"search":[105],"engines,":[106],"returned":[109],"highly-ranked":[110],"search-result":[111],"pages":[112],"are":[113],"used":[114],"describe":[116],"them.":[117]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
