{"id":"https://openalex.org/W2395337565","doi":"https://doi.org/10.3233/978-1-61499-289-9-667","title":"Identifying Unproven Cancer Treatments on the Health Web: Addressing Accuracy, Generalizability and Scalability","display_name":"Identifying Unproven Cancer Treatments on the Health Web: Addressing Accuracy, Generalizability and Scalability","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2395337565","doi":"https://doi.org/10.3233/978-1-61499-289-9-667","mag":"2395337565","pmid":"https://pubmed.ncbi.nlm.nih.gov/23920640"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-289-9-667","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-289-9-667","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aphinyanaphongs Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aphinyanaphongs Yin","raw_affiliation_strings":["Center for Health Informatics and Bioinformatics, NYU Langone Medical Center, NY, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Health Informatics and Bioinformatics, NYU Langone Medical Center, NY, NY, USA","institution_ids":["https://openalex.org/I4210086933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010276623","display_name":"Lawrence D. Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu Lawrence D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113735333","display_name":"Constantin Aliferis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aliferis Constantin F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7777,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93556785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"192","issue":null,"first_page":"667","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12878","display_name":"Pharmaceutical Quality and Counterfeiting","score":0.9732999801635742,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.9448213577270508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773582935333252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7641762495040894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6285803914070129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5228155851364136},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.47443878650665283},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4494308829307556},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40954315662384033},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34850287437438965},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15717020630836487}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9448213577270508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773582935333252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7641762495040894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6285803914070129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228155851364136},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.47443878650665283},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4494308829307556},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40954315662384033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34850287437438965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15717020630836487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003257","descriptor_name":"Consumer Product Safety","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003257","descriptor_name":"Consumer Product Safety","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003257","descriptor_name":"Consumer Product Safety","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003257","descriptor_name":"Consumer Product Safety","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D008389","descriptor_name":"Marketing of Health Services","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000628","qualifier_name":"therapy","is_major_topic":false},{"descriptor_ui":"D011785","descriptor_name":"Quality Assurance, Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011785","descriptor_name":"Quality Assurance, Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011785","descriptor_name":"Quality Assurance, Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011785","descriptor_name":"Quality Assurance, Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D017063","descriptor_name":"Outcome Assessment, Health Care","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019317","descriptor_name":"Evidence-Based Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019317","descriptor_name":"Evidence-Based Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019317","descriptor_name":"Evidence-Based Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019317","descriptor_name":"Evidence-Based Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.3233/978-1-61499-289-9-667","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-289-9-667","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:23920640","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23920640","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4162393","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4162393","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4162393","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Stud Health Technol Inform","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4162393","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G53965780","display_name":null,"funder_award_id":"UL1RR029893","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G840352361","display_name":null,"funder_award_id":"1UL1 RR029893","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1563448312","https://openalex.org/W1902141597","https://openalex.org/W1911697890","https://openalex.org/W2041801408","https://openalex.org/W2049410638","https://openalex.org/W2057718909","https://openalex.org/W2059611964","https://openalex.org/W2067096656","https://openalex.org/W2087025987","https://openalex.org/W2108034425","https://openalex.org/W2108655328","https://openalex.org/W2133091666","https://openalex.org/W2138911192","https://openalex.org/W2161257811","https://openalex.org/W2167262896","https://openalex.org/W2173213060","https://openalex.org/W2415661127"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2388888344"],"abstract_inverted_index":{"Building":[0],"machine":[1],"learning":[2],"models":[3,47,55,75,126,195],"that":[4,135],"identify":[5,152],"unproven":[6,142,153,159],"cancer":[7,143],"treatments":[8,60,144,154,160],"on":[9,84,155],"the":[10,20,33,63,67,70,85,104,122,125,156,180,189],"Health":[11,86],"Web":[12],"is":[13,145,171,185],"a":[14,137,149],"promising":[15],"approach":[16],"for":[17],"dealing":[18],"with":[19,196],"dissemination":[21],"of":[22,36,41,69,82,124,141,179],"false":[23],"and":[24,92,99,108,168,177,191,193],"dangerous":[25],"information":[26],"to":[27,58,80,120,127,147,151,164,187],"vulnerable":[28],"health":[29],"consumers.":[30],"Aside":[31],"from":[32],"obvious":[34],"requirement":[35],"accuracy,":[37],"two":[38],"issues":[39],"are":[40],"practical":[42],"importance":[43],"in":[44,48,66],"deploying":[45],"these":[46],"real":[49],"world":[50],"applications.":[51],"(a)":[52,136],"Generalizability:":[53],"The":[54,74,130],"must":[56],"generalize":[57],"all":[59],"(not":[61],"just":[62],"ones":[64],"used":[65],"training":[68],"models).":[71],"(b)":[72,158],"Scalability:":[73],"can":[76],"be":[77],"applied":[78],"efficiently":[79],"billions":[81],"documents":[83],"Web.":[87],"First,":[88],"we":[89,117],"provide":[90],"methods":[91],"related":[93],"empirical":[94],"data":[95],"demonstrating":[96],"strong":[97],"accuracy":[98],"generalizability.":[100],"Second,":[101],"by":[102],"combining":[103],"MapReduce":[105],"distributed":[106,175],"architecture":[107],"high":[109],"dimensionality":[110],"compression":[111],"via":[112],"Markov":[113],"Boundary":[114],"feature":[115,182],"selection,":[116,183],"show":[118],"how":[119],"scale":[121],"application":[123],"WWW-scale":[128],"corpora.":[129],"present":[131],"work":[132],"provides":[133],"evidence":[134],"very":[138],"small":[139],"subset":[140],"sufficient":[146],"build":[148,192],"model":[150],"web;":[157],"use":[161],"distinct":[162],"language":[163,170],"market":[165],"their":[166],"claims":[167],"this":[169],"learnable;":[172],"(c)":[173],"through":[174],"parallelization":[176],"state":[178],"art":[181],"it":[184],"possible":[186],"prepare":[188],"corpora":[190],"apply":[194],"large":[197],"scalability.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
