{"id":"https://openalex.org/W2041013277","doi":"https://doi.org/10.1145/1643823.1643852","title":"Semantic document classification and keyword spotting in digital repositories","display_name":"Semantic document classification and keyword spotting in digital repositories","publication_year":2009,"publication_date":"2009-10-27","ids":{"openalex":"https://openalex.org/W2041013277","doi":"https://doi.org/10.1145/1643823.1643852","mag":"2041013277"},"language":"en","primary_location":{"id":"doi:10.1145/1643823.1643852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1643823.1643852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Management of Emergent Digital EcoSystems","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/A5032535028","display_name":"Nikunj Yadav","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nikunj Yadav","raw_affiliation_strings":["Indian Institute of Information Technology, Allahabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045568254","display_name":"Yanu Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yanu Gupta","raw_affiliation_strings":["Indian Institute of Information Technology, Allahabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018728658","display_name":"Manish Kumar","orcid":"https://orcid.org/0000-0002-1311-0976"},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Kumar","raw_affiliation_strings":["Indian Institute of Information Technology, Allahabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012899344","display_name":"Ratna Sanyal","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ratna Sanyal","raw_affiliation_strings":["Indian Institute of Information Technology, Allahabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Allahabad, India","institution_ids":["https://openalex.org/I26072440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26072440"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10030503,"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":"157","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9962999820709229,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8851309418678284},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7362319231033325},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5718427300453186},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5704750418663025},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4843395948410034},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4764711856842041},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4723342955112457},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4120277762413025},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32492953538894653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2753085494041443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851309418678284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7362319231033325},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5718427300453186},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5704750418663025},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4843395948410034},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4764711856842041},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4723342955112457},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4120277762413025},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32492953538894653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2753085494041443},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1643823.1643852","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1643823.1643852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Management of Emergent Digital EcoSystems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318053","display_name":"Indian Institute of Information Technology, Allahabad","ror":"https://ror.org/03rgjt374"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1572659166","https://openalex.org/W2049633694","https://openalex.org/W2107743791","https://openalex.org/W2119821739","https://openalex.org/W2134731454","https://openalex.org/W4301856958"],"related_works":["https://openalex.org/W2538371562","https://openalex.org/W3046994506","https://openalex.org/W2045631426","https://openalex.org/W1751894661","https://openalex.org/W4238415164","https://openalex.org/W2137763598","https://openalex.org/W932910286","https://openalex.org/W2545327431","https://openalex.org/W2142127980","https://openalex.org/W2997283289"],"abstract_inverted_index":{"The":[0],"volume":[1],"of":[2,73,104],"documents":[3,30,51,65,75],"in":[4,9,31,52],"the":[5,37,50,58,68,71,74,93,99,105],"digital":[6,54],"repositories":[7],"numbers":[8],"thousands":[10],"and":[11,27,56,70,91,102],"is":[12],"increasing":[13],"constantly.":[14],"In":[15,40],"such":[16],"a":[17,21,32,45,53],"scenario":[18],"it":[19],"becomes":[20],"very":[22],"important":[23],"issue":[24],"to":[25,36,48,63,66,88],"organize":[26,89],"retrieve":[28],"these":[29],"way":[33],"that":[34],"relates":[35],"human":[38],"mind.":[39],"this":[41,79],"paper,":[42],"we":[43],"present":[44],"novel":[46],"approach":[47,78,97],"classify":[49],"repository":[55],"find":[57],"semantically":[59],"significant":[60],"keywords":[61],"related":[62],"those":[64],"make":[67],"organization":[69],"retrieval":[72],"expeditious.":[76],"We":[77],"problem":[80],"using":[81],"probabilistic":[82],"model":[83],"with":[84,110],"incomplete":[85],"training":[86],"data":[87],"them":[90],"mark":[92],"relevant":[94],"keywords.":[95],"This":[96],"makes":[98],"classification":[100,109],"faster":[101],"instead":[103],"unlabeled":[106],"clustering":[107],"gives":[108],"well":[111],"defined":[112],"topics.":[113]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
