{"id":"https://openalex.org/W2045417210","doi":"https://doi.org/10.1145/2034691.2034733","title":"Building a topic hierarchy using the bag-of-related-words representation","display_name":"Building a topic hierarchy using the bag-of-related-words representation","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W2045417210","doi":"https://doi.org/10.1145/2034691.2034733","mag":"2045417210"},"language":"en","primary_location":{"id":"doi:10.1145/2034691.2034733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document 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/A5040365453","display_name":"Rafael Geraldeli Rossi","orcid":"https://orcid.org/0000-0001-8513-3213"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Rafael Geraldeli Rossi","raw_affiliation_strings":["Institute of Mathematics and Computer Science - University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Science - University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073365814","display_name":"Solange Oliveira Rezende","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Solange Oliveira Rezende","raw_affiliation_strings":["Institute of Mathematics and Computer Science - University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Science - University of S\u00e3o Paulo, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040365453"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":3.0368,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91707162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.6572931408882141},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.64306640625},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6334707140922546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4876827001571655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.455265074968338},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3450479507446289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572931408882141},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.64306640625},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6334707140922546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4876827001571655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.455265074968338},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3450479507446289},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2034691.2034733","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W114024208","https://openalex.org/W400277577","https://openalex.org/W1506285740","https://openalex.org/W1576676390","https://openalex.org/W1660390307","https://openalex.org/W1833785989","https://openalex.org/W1875492311","https://openalex.org/W1892638773","https://openalex.org/W1971318281","https://openalex.org/W1981137801","https://openalex.org/W2009512022","https://openalex.org/W2024175727","https://openalex.org/W2027875450","https://openalex.org/W2065793456","https://openalex.org/W2066277072","https://openalex.org/W2102297485","https://openalex.org/W2114134542","https://openalex.org/W2126482906","https://openalex.org/W2129630294","https://openalex.org/W2131750090","https://openalex.org/W2143894822","https://openalex.org/W2322253478","https://openalex.org/W2911687881","https://openalex.org/W6637101025","https://openalex.org/W6988007563"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W2509431957","https://openalex.org/W2026999166","https://openalex.org/W1599954583","https://openalex.org/W1992685502","https://openalex.org/W4211007821","https://openalex.org/W2802395037","https://openalex.org/W4389565704","https://openalex.org/W1996802783","https://openalex.org/W3204019825"],"abstract_inverted_index":{"A":[0],"simple":[1],"and":[2,32,87,166,200],"intuitive":[3],"way":[4,51],"to":[5,22,52,118,151,159,169],"organize":[6],"a":[7,13,24,39,64,74,123,129,144,201],"huge":[8],"document":[9,30,42,60,71,142,154],"collection":[10,72,145],"is":[11,44,48,61,116,223],"by":[12,63,98,122],"topic":[14,25,187,205,230],"hierarchy.":[15],"Generally":[16],"two":[17],"steps":[18],"are":[19,96,137,175],"carried":[20,191],"out":[21,192],"build":[23],"hierarchy":[26,188,231],"automatically:":[27],"1)":[28],"hierarchical":[29],"clustering":[31,198],"2)":[33],"cluster":[34],"labeling.":[35],"For":[36],"both":[37],"steps,":[38],"good":[40],"textual":[41,141],"representation":[43,222],"essential.":[45],"The":[46,135,215],"bag-of-words":[47,227],"the":[49,70,84,94,133,153,161,171,181,186,197,208,213,220,226,229],"common":[50],"represent":[53],"text":[54],"collections.":[55],"In":[56,109],"this":[57,110],"representation,":[58],"each":[59,67,140],"represented":[62],"vector":[65],"where":[66],"word":[68],"in":[69,157],"represents":[73],"dimension":[75],"(feature).":[76],"This":[77],"approach":[78,113,183],"has":[79],"well":[80],"known":[81],"problems":[82],"as":[83,103],"high":[85],"dimensionality":[86,130],"sparsity":[88],"of":[89,93,125,143,163,173],"data.":[90],"Besides,":[91],"most":[92],"concepts":[95],"composed":[97],"more":[99],"than":[100,132,225],"one":[101],"word,":[102],"\"document":[104],"engineering\"":[105],"or":[106],"\"text":[107],"mining\".":[108],"paper":[111],"an":[112,193],"called":[114],"bag-of-related-words":[115],"proposed":[117,182,221],"generate":[119],"features":[120,136,174],"compounded":[121],"set":[124],"related":[126],"words":[127],"with":[128,212],"smaller":[131],"bag-of-words.":[134,214],"extracted":[138],"from":[139],"using":[146],"association":[147,164],"rules.":[148],"Different":[149],"ways":[150],"map":[152],"into":[155],"transactions":[156],"order":[158],"allow":[160],"extraction":[162],"rules":[165],"interest":[167],"measures":[168],"prune":[170],"number":[172],"analyzed.":[176],"To":[177],"evaluate":[178],"how":[179],"much":[180],"can":[184],"aid":[185],"building,":[189],"we":[190],"objective":[194],"evaluation":[195,203],"for":[196,204,228],"structure,":[199],"subjective":[202],"hierarchies.":[206],"All":[207],"results":[209,217],"were":[210],"compared":[211],"obtained":[216],"demonstrated":[218],"that":[219],"better":[224],"building.":[232]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"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"}