{"id":"https://openalex.org/W2113043986","doi":"https://doi.org/10.1145/1008992.1009036","title":"Parameterized generation of labeled datasets for text categorization based on a hierarchical directory","display_name":"Parameterized generation of labeled datasets for text categorization based on a hierarchical directory","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2113043986","doi":"https://doi.org/10.1145/1008992.1009036","mag":"2113043986"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5034956621","display_name":"Dmitry Davidov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Dmitry Davidov","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013932834","display_name":"Evgeniy Gabrilovich","orcid":"https://orcid.org/0000-0001-7933-1926"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Evgeniy Gabrilovich","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088024319","display_name":"Shaul Markovitch","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shaul Markovitch","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034956621"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":7.8562,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.97223229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.8445162773132324},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.8226423263549805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966381311416626},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7288112640380859},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5697023272514343},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4990520477294922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42388206720352173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37599506974220276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3245905041694641},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06834405660629272}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.8445162773132324},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.8226423263549805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966381311416626},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7288112640380859},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5697023272514343},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4990520477294922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42388206720352173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37599506974220276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3245905041694641},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06834405660629272},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1008992.1009036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.1415","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.1415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.technion.ac.il/~shaulm/papers/sigir2004-gabrilovich.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W116763023","https://openalex.org/W136846643","https://openalex.org/W140312209","https://openalex.org/W1482260847","https://openalex.org/W1493526108","https://openalex.org/W1504694836","https://openalex.org/W1569415500","https://openalex.org/W1576520375","https://openalex.org/W1604938182","https://openalex.org/W1659833910","https://openalex.org/W1978329176","https://openalex.org/W1999776614","https://openalex.org/W2010118680","https://openalex.org/W2019771121","https://openalex.org/W2028962062","https://openalex.org/W2035344247","https://openalex.org/W2038721957","https://openalex.org/W2050559027","https://openalex.org/W2063862666","https://openalex.org/W2071664212","https://openalex.org/W2076498403","https://openalex.org/W2084134149","https://openalex.org/W2084812512","https://openalex.org/W2107143175","https://openalex.org/W2112642950","https://openalex.org/W2118020653","https://openalex.org/W2125055259","https://openalex.org/W2133002765","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2156909104","https://openalex.org/W2170120409","https://openalex.org/W2170602716","https://openalex.org/W2170654002","https://openalex.org/W2977393556","https://openalex.org/W3003709066","https://openalex.org/W3017143921","https://openalex.org/W4235505822","https://openalex.org/W6604709370","https://openalex.org/W6634442568","https://openalex.org/W6684837874","https://openalex.org/W6776565550","https://openalex.org/W7019491504"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"Although":[0],"text":[1,34],"categorization":[2,35,84,113],"is":[3],"a":[4,22,96,120],"burgeoning":[5],"area":[6],"of":[7,46,52,64,95,112,137],"IR":[8],"research,":[9],"readily":[10],"available":[11,143],"test":[12],"collections":[13],"in":[14,49,78],"this":[15],"field":[16],"are":[17,106,141],"surprisingly":[18],"scarce.":[19],"We":[20,61],"describe":[21],"methodology":[23],"and":[24,122],"system":[25],"(named":[26],"ACCIO)":[27],"for":[28,33,127,144],"automatically":[29,138],"acquiring":[30],"labeled":[31],"datasets":[32,73,129,140],"from":[36],"the":[37,44,50,58,93,100],"World":[38],"Wide":[39],"Web,":[40],"by":[41,98],"capitalizing":[42],"on":[43,119],"body":[45],"knowledge":[47],"encoded":[48],"structure":[51],"existing":[53],"hierarchical":[54],"directories":[55],"such":[56],"as":[57,124],"Open":[59],"Directory.":[60],"define":[62],"parameters":[63],"categories":[65],"that":[66,91,115],"make":[67],"it":[68],"possible":[69],"to":[70,108,131,147],"acquire":[71],"numerous":[72],"with":[74],"desired":[75],"properties,":[76],"which":[77],"turn":[79],"allow":[80],"better":[81],"control":[82],"over":[83],"experiments.":[85],"In":[86],"particular,":[87],"we":[88],"develop":[89],"metrics":[90,105],"estimate":[92],"difficulty":[94],"dataset":[97],"examining":[99],"host":[101],"directory":[102],"structure.":[103],"These":[104],"shown":[107],"be":[109,117],"good":[110],"predictors":[111],"accuracy":[114],"can":[116],"achieved":[118],"dataset,":[121],"serve":[123],"efficient":[125],"heuristics":[126],"generating":[128],"subject":[130],"user's":[132],"requirements.":[133],"A":[134],"large":[135],"collection":[136],"generated":[139],"made":[142],"other":[145],"researchers":[146],"use.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}