{"id":"https://openalex.org/W1981853208","doi":"https://doi.org/10.1145/564376.564471","title":"Building thematic lexical resources by term categorization","display_name":"Building thematic lexical resources by term categorization","publication_year":2002,"publication_date":"2002-08-11","ids":{"openalex":"https://openalex.org/W1981853208","doi":"https://doi.org/10.1145/564376.564471","mag":"1981853208"},"language":"en","primary_location":{"id":"doi:10.1145/564376.564471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/564376.564471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th 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/A5073069826","display_name":"Alberto Lavelli","orcid":"https://orcid.org/0000-0002-7175-6804"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alberto Lavelli","raw_affiliation_strings":["ITC-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"ITC-irst, Trento, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066077296","display_name":"Bernardo Magnini","orcid":"https://orcid.org/0000-0002-0740-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernardo Magnini","raw_affiliation_strings":["ITC-irst, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"ITC-irst, Trento, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063975186","display_name":"Fabrizio Sebastiani","orcid":"https://orcid.org/0000-0003-4221-6427"},"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":false,"raw_author_name":"Fabrizio Sebastiani","raw_affiliation_strings":["Istituto di Elaborazione dell'Informazione, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Elaborazione dell'Informazione, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073069826"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4261,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68123013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"415","last_page":"416"},"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":0.986299991607666,"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":0.9858999848365784,"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/categorization","display_name":"Categorization","score":0.8643302917480469},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8032761812210083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7625076770782471},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7202029824256897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6435065269470215},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6289528608322144},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5070717334747314},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.49698832631111145},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4969082176685333},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.43982183933258057},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.41349172592163086},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3883529603481293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09453243017196655}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8643302917480469},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8032761812210083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625076770782471},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7202029824256897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6435065269470215},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6289528608322144},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5070717334747314},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.49698832631111145},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4969082176685333},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.43982183933258057},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.41349172592163086},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3883529603481293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09453243017196655},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/564376.564471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/564376.564471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:hdl:10068/313271","is_oa":false,"landing_page_url":"http://hdl.handle.net/10068/313271","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Y - Progress report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.3814","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.3814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faure.iei.pi.cnr.it/~fabrizio/Publications/2002-TR-09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.880.2727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.880.2727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Fabrizio_Sebastiani/publication/2533190_Building_Thematic_Lexical_Resources_by_Term_Categorization/links/5510e1ab0cf20352196cc974.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W22702538","https://openalex.org/W108247077","https://openalex.org/W151200788","https://openalex.org/W626879319","https://openalex.org/W1504008138","https://openalex.org/W1515865104","https://openalex.org/W1527325405","https://openalex.org/W1529196404","https://openalex.org/W1540182703","https://openalex.org/W1553682320","https://openalex.org/W1562842039","https://openalex.org/W1569550005","https://openalex.org/W1572870503","https://openalex.org/W1576520375","https://openalex.org/W1576676390","https://openalex.org/W1590686500","https://openalex.org/W1956559956","https://openalex.org/W1978394996","https://openalex.org/W1979648751","https://openalex.org/W1983078185","https://openalex.org/W1987996059","https://openalex.org/W2002675557","https://openalex.org/W2009051249","https://openalex.org/W2010978120","https://openalex.org/W2014706780","https://openalex.org/W2027819720","https://openalex.org/W2038721957","https://openalex.org/W2040004971","https://openalex.org/W2040424159","https://openalex.org/W2045577803","https://openalex.org/W2047959359","https://openalex.org/W2052690453","https://openalex.org/W2053463056","https://openalex.org/W2063862666","https://openalex.org/W2105378642","https://openalex.org/W2107434887","https://openalex.org/W2107668593","https://openalex.org/W2110529160","https://openalex.org/W2118020653","https://openalex.org/W2126502509","https://openalex.org/W2149671658","https://openalex.org/W2151375725","https://openalex.org/W2153211312","https://openalex.org/W2161669948","https://openalex.org/W2163953154","https://openalex.org/W2170355247","https://openalex.org/W2170670430","https://openalex.org/W2172142456","https://openalex.org/W2439017901","https://openalex.org/W6600892715"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2109941374","https://openalex.org/W2134032133"],"abstract_inverted_index":{"We":[0],"discuss":[1],"the":[2,29,106,195],"automatic":[3],"generation":[4,30],"of":[5,10,31,38,51,70,79,90,120,137,151,157,178,190,197,204],"thematic":[6,200],"lexicons":[7,33],"by":[8,103],"means":[9],"term":[11,139],"categorization,":[12,105],"a":[13,65,72,88,117,135,149,162,176,188,199],"novel":[14],"task":[15],"employing":[16],"techniques":[17],"from":[18,82,116],"information":[19],"retrieval":[20],"(IR)":[21],"and":[22,45,87,153,182],"machine":[23],"learning":[24,39,163],"(ML).":[25],"Specifically,":[26],"we":[27,165],"view":[28],"such":[32],"as":[34,97,132,146],"an":[35,83,202],"iterative":[36],"process":[37,54,196],"previously":[40],"unknown":[41],"associations":[42],"between":[43],"terms":[44,144,155],"themes":[46],"(i.e.":[47],"disciplines,":[48],"or":[49,122],"fields":[50],"activity).":[52],"The":[53,99],"is":[55,101],"iterative,":[56],"in":[57,64,134,148,175],"that":[58],"it":[59,170,184],"generates,":[60],"for":[61,187],"each":[62],"ci":[63],"set":[66,89,119],"C":[67],"=":[68,94],"{c1,...,cm}":[69],"themes,":[71,121],"sequence":[73],"Li0\u2286":[74],"Li1\u2286":[75],"...":[76],"\u2286":[77],"Lin":[78],"lexicons,":[80],"bootstrapping":[81],"initial":[84],"lexicon":[85,201],"Li0":[86],"text":[91,104,126,179],"corpora":[92],"\u0398":[93],"{\u03b80,...,\u03b8n-1}":[95],"given":[96],"input.":[98],"method":[100],"inspired":[102],"discipline":[107],"concerned":[108],"with":[109,114,129,143,159],"labelling":[110],"natural":[111],"language":[112],"texts":[113],"labels":[115,154],"predefined":[118],"categories.":[123],"However,":[124],"while":[125],"categorization":[127,140,180],"deals":[128,141],"documents":[130],"represented":[131,145],"vectors":[133,147],"space":[136,150],"terms,":[138],"(dually)":[142],"documents,":[152],"(instead":[156],"documents)":[158],"themes.":[160],"As":[161],"device":[164],"adopt":[166],"boosting,":[167],"since":[168],"(a)":[169],"has":[171],"demonstrated":[172],"state-of-the-art":[173],"effectiveness":[174],"variety":[177],"applications,":[181],"(b)":[183],"naturally":[185],"allows":[186],"form":[189],"\"data":[191],"cleaning\",":[192],"thereby":[193],"making":[194],"generating":[198],"iteration":[203],"generate-and-test":[205],"steps.":[206]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}