{"id":"https://openalex.org/W2145746338","doi":"https://doi.org/10.1109/icdim.2008.4746750","title":"Using the augmented vector space model to support the knowledge worker in document filtering","display_name":"Using the augmented vector space model to support the knowledge worker in document filtering","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2145746338","doi":"https://doi.org/10.1109/icdim.2008.4746750","mag":"2145746338"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","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/A5100893983","display_name":"A. Michael Johnston","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]},{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Ann Johnston","raw_affiliation_strings":["Hewlett Packard Company, India","Hewlett-Packard, USA"],"affiliations":[{"raw_affiliation_string":"Hewlett Packard Company, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009677323","display_name":"Francesco Lelli","orcid":"https://orcid.org/0000-0003-1900-9171"},"institutions":[{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Francesco Lelli","raw_affiliation_strings":["University of Lugano, Switzerland","University of Lugano, USA"],"affiliations":[{"raw_affiliation_string":"University of Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]},{"raw_affiliation_string":"University of Lugano, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071104283","display_name":"Stefan Decker","orcid":"https://orcid.org/0000-0001-6324-7164"},"institutions":[{"id":"https://openalex.org/I181231927","display_name":"National University of Ireland","ror":"https://ror.org/00shsf120","country_code":"IE","type":"education","lineage":["https://openalex.org/I181231927"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Stefan Decker","raw_affiliation_strings":["National University of Ireland, Ireland"],"affiliations":[{"raw_affiliation_string":"National University of Ireland, Ireland","institution_ids":["https://openalex.org/I181231927"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100893983"],"corresponding_institution_ids":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"],"apc_list":null,"apc_paid":null,"fwci":0.572,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79402657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"710","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9947999715805054,"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":0.9944999814033508,"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/workbench","display_name":"Workbench","score":0.8728867173194885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921718955039978},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.7499580383300781},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7411033511161804},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6339880228042603},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5792555809020996},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5125613212585449},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44546711444854736},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4301396310329437},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4141318202018738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29077672958374023},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.10305672883987427}],"concepts":[{"id":"https://openalex.org/C2779145975","wikidata":"https://www.wikidata.org/wiki/Q347690","display_name":"Workbench","level":3,"score":0.8728867173194885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921718955039978},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.7499580383300781},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7411033511161804},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6339880228042603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5792555809020996},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5125613212585449},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44546711444854736},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4301396310329437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4141318202018738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29077672958374023},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.10305672883987427},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2008.4746750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","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":11,"referenced_works":["https://openalex.org/W1534714852","https://openalex.org/W1833785989","https://openalex.org/W1956559956","https://openalex.org/W2063862666","https://openalex.org/W2099503932","https://openalex.org/W2117030594","https://openalex.org/W2118020653","https://openalex.org/W2136729221","https://openalex.org/W2165612380","https://openalex.org/W2325227998","https://openalex.org/W4252417799"],"related_works":["https://openalex.org/W2003237777","https://openalex.org/W2163228021","https://openalex.org/W2376070138","https://openalex.org/W2386166348","https://openalex.org/W2378013939","https://openalex.org/W2000139977","https://openalex.org/W2004087619","https://openalex.org/W1665725731","https://openalex.org/W4321472216","https://openalex.org/W2557094866"],"abstract_inverted_index":{"In":[0],"the":[1,4,18,51,64,73,77,81],"current":[2,24],"age":[3],"discovery":[5],"of":[6,34,72,80],"relevant":[7],"information":[8,38,67],"is":[9,46],"becoming":[10],"extremely":[11],"difficult.":[12],"Users":[13],"must":[14],"manually":[15],"search":[16,25],"through":[17],"high-recall,":[19],"low-precision":[20],"results":[21],"produced":[22],"by":[23,50],"engines.":[26],"We":[27],"propose":[28],"a":[29,47],"process":[30,62,74],"which":[31],"incorporates":[32],"benefits":[33],"automated":[35],"and":[36],"manual":[37],"extraction.":[39],"The":[40],"HSC":[41],"workbench":[42],"(Hierarchical":[43],"Step-wise":[44],"Categorization)":[45],"tool":[48],"developed":[49],"Hewlett-Packard":[52],"Research":[53],"Group":[54],"in":[55,66],"HP,":[56],"ESC":[57],"Galway.":[58],"It":[59],"implements":[60],"this":[61],"supporting":[63],"user":[65,78],"filtering":[68],"tasks,":[69],"automating":[70],"segments":[71],"but":[75],"giving":[76],"control":[79],"categorization.":[82]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
