{"id":"https://openalex.org/W2054808906","doi":"https://doi.org/10.1145/2494266.2494279","title":"Interactive text document clustering using feature labeling","display_name":"Interactive text document clustering using feature labeling","publication_year":2013,"publication_date":"2013-09-03","ids":{"openalex":"https://openalex.org/W2054808906","doi":"https://doi.org/10.1145/2494266.2494279","mag":"2054808906"},"language":"en","primary_location":{"id":"doi:10.1145/2494266.2494279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 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/A5113643083","display_name":"Seyednaser Nourashrafeddin","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Seyednaser Nourashrafeddin","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083914227","display_name":"Dirk V. Arnold","orcid":"https://orcid.org/0000-0001-5367-6862"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dirk Arnold","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113643083"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":3.3663,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92618541,"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":"61","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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":0.9988999962806702,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976000189781189,"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":0.8009713888168335},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7971543073654175},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7411715984344482},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6816911697387695},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5835109353065491},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5735207200050354},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5270538330078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5014486312866211},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4658110439777374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39716801047325134},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3908711075782776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32457882165908813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009713888168335},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7971543073654175},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7411715984344482},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6816911697387695},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5835109353065491},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5735207200050354},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5270538330078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5014486312866211},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4658110439777374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39716801047325134},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3908711075782776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32457882165908813},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2494266.2494279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2494266.2494279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W173851765","https://openalex.org/W204086241","https://openalex.org/W1501827958","https://openalex.org/W1517548115","https://openalex.org/W1523389133","https://openalex.org/W1531719573","https://openalex.org/W1596382552","https://openalex.org/W1636513602","https://openalex.org/W1970187450","https://openalex.org/W2084026949","https://openalex.org/W2089507600","https://openalex.org/W2096100960","https://openalex.org/W2102524069","https://openalex.org/W2113076747","https://openalex.org/W2116237179","https://openalex.org/W2120413916","https://openalex.org/W2121947440","https://openalex.org/W2125327503","https://openalex.org/W2134089414","https://openalex.org/W2139224176","https://openalex.org/W2153839362","https://openalex.org/W2560674852","https://openalex.org/W6633864139"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"We":[0,78,103],"propose":[1,45],"an":[2],"interactive":[3,106,112],"text":[4,48,120],"document":[5,25,58],"method,":[6],"which":[7],"is":[8,136],"based":[9],"on":[10,116],"term":[11,51,67,92,107,113,134,142],"labeling.":[12],"The":[13,28,122],"algorithm":[14,115],"asks":[15],"the":[16,20,35,66,140],"user":[17,131],"to":[18,33,73,84,99,109],"cluster":[19,100],"top":[21],"keyterms":[22],"associated":[23,88],"with":[24,89,126],"clusters":[26,30,68],"iteratively.":[27],"keyterm":[29],"are":[31,60,69,96],"used":[32,98],"guide":[34],"clustering":[36,42],"method.":[37,144],"Rather":[38],"than":[39,139],"using":[40,50],"standard":[41,119],"algorithms,":[43],"we":[44],"a":[46,57,63,81,110,127],"new":[47],"clusterer":[49],"clusters.":[52],"Terms":[53],"that":[54,125],"exist":[55],"in":[56,71],"corpus":[59],"clustered.":[61],"Using":[62],"greedy":[64],"approach,":[65],"distilled":[70,91],"order":[72],"remove":[74],"non-discriminative":[75],"general":[76],"terms.":[77],"then":[79],"present":[80],"heuristic":[82],"approach":[83],"extract":[85],"seed":[86],"documents":[87],"each":[90],"cluster.":[93],"These":[94],"seeds":[95],"finally":[97],"all":[101],"documents.":[102],"compared":[104],"our":[105,133],"labeling":[108,135],"baseline":[111,141],"selection":[114,143],"some":[117],"real":[118],"datasets.":[121],"experiments":[123],"show":[124],"comparable":[128],"amount":[129],"of":[130],"effort,":[132],"more":[137],"effective":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}