{"id":"https://openalex.org/W2171506566","doi":"https://doi.org/10.1145/1596515.1596516","title":"Improving text categorization bootstrapping via unsupervised learning","display_name":"Improving text categorization bootstrapping via unsupervised learning","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2171506566","doi":"https://doi.org/10.1145/1596515.1596516","mag":"2171506566"},"language":"en","primary_location":{"id":"doi:10.1145/1596515.1596516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1596515.1596516","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-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/A5087419620","display_name":"Alfio Gliozzo","orcid":"https://orcid.org/0000-0002-8044-2911"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alfio Gliozzo","raw_affiliation_strings":["STLab-ISTC-CNR, Rome"],"affiliations":[{"raw_affiliation_string":"STLab-ISTC-CNR, Rome","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006685038","display_name":"Carlo Strapparava","orcid":"https://orcid.org/0000-0002-9365-0242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlo Strapparava","raw_affiliation_strings":["FBK-IRST, Povo"],"affiliations":[{"raw_affiliation_string":"FBK-IRST, Povo","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033006575","display_name":"Ido Dagan","orcid":"https://orcid.org/0000-0003-3415-3374"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ido Dagan","raw_affiliation_strings":["Bar Ilan University"],"affiliations":[{"raw_affiliation_string":"Bar Ilan University","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087419620"],"corresponding_institution_ids":["https://openalex.org/I122991210"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88427366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9883000254631042,"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.8723410964012146},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8464179635047913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7427292466163635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6669507026672363},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6438332796096802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5520433187484741},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5484564304351807},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49115678668022156},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4595543146133423},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4471582770347595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42205724120140076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20806562900543213},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11109089851379395}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.8723410964012146},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8464179635047913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427292466163635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6669507026672363},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6438332796096802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5520433187484741},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5484564304351807},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49115678668022156},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4595543146133423},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4471582770347595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42205724120140076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20806562900543213},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11109089851379395},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1596515.1596516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1596515.1596516","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.6983","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.6983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://u.cs.biu.ac.il/~dagan/publications/a1-gliozzo-from journal site.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unitn.it:11572/343409","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/343409","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W22702538","https://openalex.org/W136846643","https://openalex.org/W265767496","https://openalex.org/W1493526108","https://openalex.org/W1500117362","https://openalex.org/W1553187123","https://openalex.org/W1560633476","https://openalex.org/W1576520375","https://openalex.org/W1730404227","https://openalex.org/W1777939696","https://openalex.org/W1918870341","https://openalex.org/W1956559956","https://openalex.org/W1981367467","https://openalex.org/W1989490498","https://openalex.org/W1995233974","https://openalex.org/W2011516515","https://openalex.org/W2038721957","https://openalex.org/W2048679005","https://openalex.org/W2085256060","https://openalex.org/W2096616587","https://openalex.org/W2101210369","https://openalex.org/W2118020653","https://openalex.org/W2129905273","https://openalex.org/W2129911618","https://openalex.org/W2133864802","https://openalex.org/W2147152072","https://openalex.org/W2152005244","https://openalex.org/W2154273644","https://openalex.org/W2156909104","https://openalex.org/W2159032819","https://openalex.org/W2161103800","https://openalex.org/W2166843810","https://openalex.org/W2189067371","https://openalex.org/W2785349534","https://openalex.org/W2883783597","https://openalex.org/W2999060954","https://openalex.org/W3014813097","https://openalex.org/W4230674625","https://openalex.org/W4389521028","https://openalex.org/W6634442568","https://openalex.org/W6683581212","https://openalex.org/W6805520290","https://openalex.org/W7020193950"],"related_works":["https://openalex.org/W151699219","https://openalex.org/W2085633464","https://openalex.org/W2360898036","https://openalex.org/W1966122760","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2138922887"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,118],"text-categorization":[3],"bootstrapping":[4,29],"algorithm":[5,85],"in":[6,82],"which":[7,50],"categories":[8],"are":[9],"described":[10],"by":[11],"relevant":[12,52],"seed":[13],"words.":[14],"Our":[15],"method":[16,112],"introduces":[17],"two":[18,89],"unsupervised":[19],"techniques":[20],"to":[21,36,71,79,114,117],"improve":[22],"the":[23,28,38,46,68,99,107,110],"initial":[24,103],"categorization":[25,91],"step":[26,66],"of":[27,109],"scheme:":[30],"(i)":[31],"using":[32,57,97],"latent":[33],"semantic":[34],"spaces":[35],"estimate":[37],"similarity":[39,69],"among":[40],"documents":[41,126],"and":[42,44,53,75,93],"words,":[43],"(ii)":[45],"Gaussian":[47],"mixture":[48],"algorithm,":[49],"differentiates":[51],"nonrelevant":[54],"category":[55,100],"information":[56],"statistics":[58],"from":[59],"unlabeled":[60],"examples.":[61],"In":[62,105],"particular,":[63,106],"this":[64],"second":[65],"maps":[67],"scores":[70],"class":[72],"posterior":[73],"probabilities,":[74],"therefore":[76],"reduces":[77],"sensitivity":[78],"keyword-dependent":[80],"variations":[81],"scores.":[83],"The":[84],"was":[86],"evaluated":[87],"on":[88,123],"text":[90],"tasks,":[92],"obtained":[94],"good":[95],"performance":[96,108],"only":[98],"names":[101],"as":[102],"seeds.":[104],"proposed":[111],"proved":[113],"be":[115],"equivalent":[116],"pure":[119],"supervised":[120],"approach":[121],"trained":[122],"70--160":[124],"labeled":[125],"per":[127],"category.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}