{"id":"https://openalex.org/W2151209607","doi":"https://doi.org/10.1109/icdim.2010.5664205","title":"Query-relevant document representation for text clustering","display_name":"Query-relevant document representation for text clustering","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2151209607","doi":"https://doi.org/10.1109/icdim.2010.5664205","mag":"2151209607"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2010.5664205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","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/A5081476817","display_name":"Masoud Makrehchi","orcid":"https://orcid.org/0000-0003-0287-9568"},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Masoud Makrehchi","raw_affiliation_strings":["Thomson Reuters, Eagan, MN, USA"],"affiliations":[{"raw_affiliation_string":"Thomson Reuters, Eagan, MN, USA","institution_ids":["https://openalex.org/I68384125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081476817"],"corresponding_institution_ids":["https://openalex.org/I68384125"],"apc_list":null,"apc_paid":null,"fwci":1.8042,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87871734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"132","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9939000010490417,"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":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.7559921741485596},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5668494701385498},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5417786836624146},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5402789115905762},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.531708300113678},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5147380828857422},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5124890804290771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512342095375061},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4876755475997925},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4674310088157654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4655853807926178},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.45298442244529724},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45219406485557556},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44963687658309937},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4433092772960663},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4404307007789612},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.4168052077293396},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4122791886329651},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.27872055768966675},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18344542384147644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559921741485596},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5668494701385498},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5417786836624146},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5402789115905762},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.531708300113678},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5147380828857422},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5124890804290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512342095375061},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4876755475997925},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4674310088157654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4655853807926178},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.45298442244529724},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45219406485557556},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44963687658309937},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4433092772960663},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4404307007789612},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.4168052077293396},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4122791886329651},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.27872055768966675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18344542384147644},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/icdim.2010.5664205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W237047597","https://openalex.org/W255897694","https://openalex.org/W291570921","https://openalex.org/W1545664618","https://openalex.org/W1569835270","https://openalex.org/W1931869323","https://openalex.org/W2011232895","https://openalex.org/W2014527343","https://openalex.org/W2077019270","https://openalex.org/W2096152098","https://openalex.org/W2115833276","https://openalex.org/W2117690346","https://openalex.org/W2118020653","https://openalex.org/W2142515059","https://openalex.org/W2148356795","https://openalex.org/W4236267615","https://openalex.org/W6609237920","https://openalex.org/W6609549191","https://openalex.org/W6634198501","https://openalex.org/W6669799895","https://openalex.org/W6674701899","https://openalex.org/W6677389453","https://openalex.org/W7032606057"],"related_works":["https://openalex.org/W1500125366","https://openalex.org/W2376075889","https://openalex.org/W2551770406","https://openalex.org/W2389382860","https://openalex.org/W1557970708","https://openalex.org/W2137763598","https://openalex.org/W2611108488","https://openalex.org/W1575842006","https://openalex.org/W2370875228","https://openalex.org/W1996059221"],"abstract_inverted_index":{"In":[0,24],"text":[1,31],"categorization,":[2],"one":[3],"well-known":[4],"document":[5],"representation":[6,29],"is":[7,11,33,36,50,55,70,106],"bag-of-words.":[8],"Although":[9],"it":[10,15],"simple":[12],"and":[13,21,169],"popular,":[14],"ignores":[16],"semantics,":[17],"underlying":[18],"linguistic":[19],"information,":[20],"word":[22,160],"correlations.":[23],"this":[25],"paper,":[26],"a":[27,41,53,74,99,124,137,149],"new":[28,100,146,166],"for":[30,108],"data":[32],"proposed":[34,155],"which":[35,105],"called":[37],"Bag-Of-Queries":[38],"(BOQ).":[39],"First,":[40],"taxonomy":[42,54,69],"of":[43,76,81,102,114,126,159],"the":[44,47,68,134,171],"terms":[45,78,116],"in":[46,131,148],"local":[48],"vocabulary":[49],"extracted.":[51],"Extracting":[52],"performed":[56],"by":[57],"learning":[58],"term":[59],"dependencies":[60],"using":[61,115,136],"an":[62,109],"information":[63],"theoretic":[64],"inclusion":[65],"index.":[66],"Next,":[67],"partitioned":[71],"to":[72,88,122,133],"generate":[73],"set":[75,125],"correlated":[77],"or":[79],"bag":[80,158],"queries.":[82,96,127],"Since":[83],"every":[84],"two":[85],"partitions":[86],"belong":[87],"different":[89],"concepts,":[90],"they":[91],"are":[92,129,143],"considered":[93,144],"semantically":[94],"orthogonal":[95,103],"This":[97],"provides":[98],"space":[101,151],"features,":[104,118],"necessary":[107],"efficient":[110],"categorization.":[111],"Finally,":[112],"instead":[113],"as":[117,145],"we":[119],"use":[120],"them":[121],"build":[123],"Documents":[128],"ranked":[130],"response":[132],"queries":[135],"similarity":[138,141],"measure.":[139],"The":[140,154],"indices":[142],"features":[147,168],"vector":[150],"model":[152],"representation.":[153],"approach":[156],"outperforms":[157],"based":[161],"clustering.":[162],"It":[163],"also":[164],"extracts":[165],"non-redundant":[167],"at":[170],"same":[172],"time":[173],"reduces":[174],"dimensionality.":[175]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"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"}