{"id":"https://openalex.org/W2517141375","doi":"https://doi.org/10.18653/v1/w16-2923","title":"An Information Foraging Approach to Determining the Number of Relevant Features","display_name":"An Information Foraging Approach to Determining the Number of Relevant Features","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2517141375","doi":"https://doi.org/10.18653/v1/w16-2923","mag":"2517141375"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2923","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2923","pdf_url":"https://www.aclweb.org/anthology/W16-2923.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2923.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108647490","display_name":"Brian Connolly","orcid":null},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brian Connolly","raw_affiliation_strings":["Cincinnati Children's Hospital Medical Center Burnet Ave Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Cincinnati Children's Hospital Medical Center Burnet Ave Cincinnati, OH 45229","institution_ids":["https://openalex.org/I1285204247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024687962","display_name":"Benjamin Glass","orcid":"https://orcid.org/0000-0002-2386-2557"},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Glass","raw_affiliation_strings":["Cincinnati Children's Hospital Medical Center Burnet Ave Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Cincinnati Children's Hospital Medical Center Burnet Ave Cincinnati, OH 45229","institution_ids":["https://openalex.org/I1285204247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057902242","display_name":"John Pestian","orcid":"https://orcid.org/0000-0001-5998-249X"},"institutions":[{"id":"https://openalex.org/I1285204247","display_name":"Cincinnati Children's Hospital Medical Center","ror":"https://ror.org/01hcyya48","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1285204247"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Pestian","raw_affiliation_strings":["Cincinnati Children's Hospital Medical Center 3333 Burnet Ave Cincinnati, OH 45229"],"affiliations":[{"raw_affiliation_string":"Cincinnati Children's Hospital Medical Center 3333 Burnet Ave Cincinnati, OH 45229","institution_ids":["https://openalex.org/I1285204247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108647490"],"corresponding_institution_ids":["https://openalex.org/I1285204247"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05436319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.993399977684021,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.823826253414154},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6591881513595581},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6011905074119568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5813429951667786},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5662040710449219},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5292539000511169},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5218338370323181},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.48254698514938354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4793601632118225},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47190672159194946},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4707406461238861},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39209994673728943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08033120632171631}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823826253414154},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6591881513595581},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6011905074119568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5813429951667786},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5662040710449219},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5292539000511169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5218338370323181},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.48254698514938354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4793601632118225},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47190672159194946},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4707406461238861},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39209994673728943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08033120632171631},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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:10.18653/v1/w16-2923","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2923","pdf_url":"https://www.aclweb.org/anthology/W16-2923.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2923","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2923","pdf_url":"https://www.aclweb.org/anthology/W16-2923.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.5299999713897705,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2517141375.pdf","grobid_xml":"https://content.openalex.org/works/W2517141375.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1502050276","https://openalex.org/W1522930027","https://openalex.org/W1533179050","https://openalex.org/W1597988947","https://openalex.org/W1748815599","https://openalex.org/W1849729440","https://openalex.org/W1969027200","https://openalex.org/W2017337590","https://openalex.org/W2034274945","https://openalex.org/W2040884411","https://openalex.org/W2078136197","https://openalex.org/W2103333826","https://openalex.org/W2119387367","https://openalex.org/W2124225314","https://openalex.org/W2131987814","https://openalex.org/W2134303651","https://openalex.org/W2143198961","https://openalex.org/W2150180799","https://openalex.org/W2153678774","https://openalex.org/W2156571267","https://openalex.org/W2264297261","https://openalex.org/W2435251607","https://openalex.org/W2548906386","https://openalex.org/W2904256401","https://openalex.org/W2998216295","https://openalex.org/W3045153201","https://openalex.org/W4244973361","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2368816706","https://openalex.org/W3160516639","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"For":[0],"many":[1],"types":[2],"of":[3,14,36,70,106,140,182,185],"high-dimensional":[4],"data,":[5,188],"such":[6,23,78],"as":[7,82],"natural":[8],"language":[9],"corpora,":[10],"the":[11,34,50,67,95,99,108,114,158,165,169,187],"vast":[12],"majority":[13],"extracted":[15],"variables":[16],"or":[17],"features":[18,24,71,96,166],"are":[19],"essentially":[20],"noise.":[21],"Culling":[22],"can":[25,84,190],"not":[26],"only":[27],"reveal":[28],"important":[29,141],"patterns,":[30],"but":[31],"also":[32],"improve":[33],"performance":[35],"supervised":[37],"and":[38,149,180,189],"unsupervised":[39],"machine":[40],"algorithms.":[41],"Most":[42],"research":[43],"on":[44,49,123,147],"feature":[45,132],"selection":[46],"has":[47,60],"focused":[48],"statistical":[51],"measures":[52],"used":[53],"to":[54,93,135,162,193],"rank":[55],"features.":[56,142],"Meanwhile,":[57],"little":[58],"work":[59],"been":[61],"done":[62],"developing":[63,77],"techniques":[64,79],"for":[65],"identifying":[66],"optimal":[68],"subset":[69,139],"without":[72],"repeatedly":[73],"training":[74],"models.":[75],"However,":[76],"is":[80,145,160,177],"important,":[81],"they":[83],"significantly":[85],"decrease":[86],"computation":[87],"time":[88],"while":[89],"providing":[90],"a":[91,102,119,138],"way":[92],"determine":[94,137,164],"that":[97,126,157,167],"characterize":[98,168],"classes":[100,170],"within":[101,171],"data":[103,109,151,173,196],"set,":[104],"independent":[105,181],"how":[107],"may":[110],"be":[111,191],"classified":[112],"in":[113,128],"future.":[115],"Here":[116],"we":[117],"introduce":[118],"novel":[120],"method":[121,144,159,176,184],"based":[122],"information":[124],"foraging":[125],"works":[127],"conjunction":[129],"with":[130],"existing":[131],"ranking":[133],"methods":[134],"automatically":[136],"The":[143,175],"demonstrated":[146],"simulated":[148],"linguistic":[150],"from":[152],"psychiatric":[153],"interviews.":[154],"We":[155],"show":[156],"able":[161],"accurately":[163],"both":[172],"sets.":[174],"fast,":[178],"simple,":[179],"any":[183,194],"classifying":[186],"extended":[192],"highdimensional":[195],"set.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}