{"id":"https://openalex.org/W2104045843","doi":"https://doi.org/10.1109/icdim.2008.4746732","title":"A new technique for detecting similar documents based on term co-occurrence and conceptual property of the text","display_name":"A new technique for detecting similar documents based on term co-occurrence and conceptual property of the text","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2104045843","doi":"https://doi.org/10.1109/icdim.2008.4746732","mag":"2104045843"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","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/A5008301597","display_name":"Azadeh Zamanifar","orcid":"https://orcid.org/0000-0002-2629-4794"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Azadeh Zamanifar","raw_affiliation_strings":["Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","Computer Eng. Department, Iran University of Science and Technology, Tehran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]},{"raw_affiliation_string":"Computer Eng. Department, Iran University of Science and Technology, Tehran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057087345","display_name":"Behrouz Minaei\u2010Bidgoli","orcid":"https://orcid.org/0000-0002-9327-7345"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Behrouz Minaei-Bidgoli","raw_affiliation_strings":["Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","Computer Eng. Department, Iran University of Science and Technology, Tehran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]},{"raw_affiliation_string":"Computer Eng. Department, Iran University of Science and Technology, Tehran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071488278","display_name":"Omid Kashefi","orcid":"https://orcid.org/0000-0003-2898-9853"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Omid Kashefi","raw_affiliation_strings":["Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","Computer Eng. Department, Iran University of Science and Technology, Tehran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]},{"raw_affiliation_string":"Computer Eng. Department, Iran University of Science and Technology, Tehran","institution_ids":["https://openalex.org/I67009956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008301597"],"corresponding_institution_ids":["https://openalex.org/I67009956"],"apc_list":null,"apc_paid":null,"fwci":1.1441,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84290225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3215","issue":null,"first_page":"526","last_page":"531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polysemy","display_name":"Polysemy","score":0.8988037705421448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7827756404876709},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7453196048736572},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.690077543258667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6021255254745483},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5706860423088074},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5293049812316895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5140558481216431},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.445582777261734},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.4229782223701477},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18166068196296692},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09666255116462708}],"concepts":[{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.8988037705421448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827756404876709},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7453196048736572},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.690077543258667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6021255254745483},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5706860423088074},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5293049812316895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5140558481216431},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.445582777261734},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4229782223701477},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18166068196296692},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09666255116462708},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2008.4746732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W145425800","https://openalex.org/W1481946661","https://openalex.org/W1542990879","https://openalex.org/W1568869800","https://openalex.org/W1572039004","https://openalex.org/W1886218757","https://openalex.org/W1982929936","https://openalex.org/W1990763225","https://openalex.org/W2081580037","https://openalex.org/W2106866704","https://openalex.org/W2125549296","https://openalex.org/W2136331837","https://openalex.org/W2142157430","https://openalex.org/W2147152072","https://openalex.org/W2155627431","https://openalex.org/W2157583484","https://openalex.org/W2165612380","https://openalex.org/W3146216709","https://openalex.org/W4285719527","https://openalex.org/W6605913859","https://openalex.org/W6634115543","https://openalex.org/W6682391429"],"related_works":["https://openalex.org/W2376040010","https://openalex.org/W2613880225","https://openalex.org/W2788559978","https://openalex.org/W2358036664","https://openalex.org/W2891304714","https://openalex.org/W4385239993","https://openalex.org/W2310152915","https://openalex.org/W2362895247","https://openalex.org/W4285531126","https://openalex.org/W2600654830"],"abstract_inverted_index":{"The":[0,35,48],"importance":[1],"of":[2,11,29,56,65,81,89,100,117],"detecting":[3,42],"similar":[4,23,43,76,94,111],"documents":[5,30,44,72,112],"grows":[6],"rapidly":[7],"as":[8],"the":[9,66,70,82,87,93,118],"amount":[10],"information":[12],"increases":[13],"exponentially.":[14],"This":[15],"paper":[16],"presents":[17],"a":[18,97],"new":[19],"technique":[20,37],"for":[21,41],"identifying":[22,92],"documents.":[24,95],"It":[25,68,84],"combines":[26],"statistical":[27],"properties":[28],"with":[31],"Persian":[32],"linguistic":[33],"features.":[34],"proposed":[36,49],"is":[38,51],"mostly":[39],"suited":[40],"in":[45,91],"specific":[46],"fields.":[47],"method":[50],"built":[52],"on":[53,61],"lexical":[54],"chain":[55],"important":[57],"words":[58,90],"and":[59,110,135],"based":[60],"term":[62],"co-occurrence":[63],"property":[64,80],"text.":[67],"prevents":[69],"irrelevant":[71],"to":[73,78,114,129],"be":[74,108,121],"identified":[75],"due":[77],"polysemy":[79],"words.":[83],"also":[85,107],"considers":[86],"order":[88],"If":[96],"document":[98],"consists":[99],"more":[101],"than":[102],"one":[103],"subject,":[104],"it":[105],"could":[106,120],"founded":[109],"according":[113],"different":[115],"topics":[116],"text":[119],"detected.":[122],"Our":[123],"results":[124],"shows":[125],"improved":[126],"performance":[127],"compared":[128],"existing":[130],"word-based":[131],"methods":[132],"like":[133],"LSI":[134],"VSM.":[136]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
