{"id":"https://openalex.org/W1497956894","doi":null,"title":"Explaining Documents' Classi\ufb01cations","display_name":"Explaining Documents' Classi\ufb01cations","publication_year":2011,"publication_date":"2011-03-15","ids":{"openalex":"https://openalex.org/W1497956894","mag":"1497956894"},"language":"en","primary_location":{"id":"mag:1497956894","doi":null,"is_oa":true,"landing_page_url":"https://archive.nyu.edu/handle/2451/29918?mode=full","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SSRN Electronic Journal","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://archive.nyu.edu/handle/2451/29918?mode=full","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101474247","display_name":"David Martens","orcid":"https://orcid.org/0000-0001-8397-2937","observed_orcids":["https://orcid.org/0000-0001-8397-2937"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"David Martens","raw_affiliation_strings":["UNIVERSITY OF ANTWERP*"],"raw_orcid":"https://orcid.org/0000-0001-8397-2937","affiliations":[{"raw_affiliation_string":"UNIVERSITY OF ANTWERP*","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037283651","display_name":"Foster John Provost","orcid":"https://orcid.org/0000-0002-0307-3884","observed_orcids":["https://orcid.org/0000-0002-0307-3884"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Foster Provost","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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":0.00019999999494757503,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/explainable-machine-learning","display_name":"explainable machine learning","score":0.7149999737739563},{"id":"https://openalex.org/keywords/document-classification","display_name":"document classification","score":0.9359999895095825},{"id":"https://openalex.org/keywords/high-dimensional-text-data","display_name":"high-dimensional text data","score":0.7950000166893005},{"id":"https://openalex.org/keywords/black-box-modeling","display_name":"black-box models","score":0.8339999914169312},{"id":"https://openalex.org/keywords/adult-content-detection","display_name":"adult content detection","score":0.7200000286102295},{"id":"https://openalex.org/keywords/web-page-classification","display_name":"web page classification","score":0.6710000038146973},{"id":"https://openalex.org/keywords/news-topic-classification","display_name":"news topic classification","score":0.8339999914169312},{"id":"https://openalex.org/keywords/20-newsgroups","display_name":"20 Newsgroups","score":0.9589999914169312},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.45899999141693115},{"id":"https://openalex.org/keywords/model-performance-improvement","display_name":"model performance improvement","score":0.4390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013646364212036},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5860273838043213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5683367252349854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5653910636901855},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5387322306632996},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5318217873573303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4938529133796692},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.42119142413139343},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39842426776885986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32557982206344604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3102279007434845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1030665934085846},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:1497956894","doi":null,"is_oa":true,"landing_page_url":"https://archive.nyu.edu/handle/2451/29918?mode=full","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SSRN Electronic Journal","raw_type":null},{"id":"pmh:http://hdl.handle.net/2451/29918","doi":null,"is_oa":false,"landing_page_url":"http://archive.nyu.edu/handle/2451/29918","pdf_url":null,"source":{"id":"https://openalex.org/S4377196662","display_name":"Faculty Digital Archive (New York University Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210123063","host_organization_name":"New York University Florence","host_organization_lineage":["https://openalex.org/I4210123063"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Working Paper"}],"best_oa_location":{"id":"mag:1497956894","doi":null,"is_oa":true,"landing_page_url":"https://archive.nyu.edu/handle/2451/29918?mode=full","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SSRN Electronic Journal","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W80463681","https://openalex.org/W1500667213","https://openalex.org/W1517113043","https://openalex.org/W1523293200","https://openalex.org/W1554663460","https://openalex.org/W1618905105","https://openalex.org/W1982120517","https://openalex.org/W1986539725","https://openalex.org/W2053463056","https://openalex.org/W2059586463","https://openalex.org/W2097726431","https://openalex.org/W2105776892","https://openalex.org/W2113882472","https://openalex.org/W2118274460","https://openalex.org/W2118585731","https://openalex.org/W2125055259","https://openalex.org/W2125943921","https://openalex.org/W2131064753","https://openalex.org/W2136451344","https://openalex.org/W2138745909","https://openalex.org/W2143184868","https://openalex.org/W2149684865","https://openalex.org/W2153635508","https://openalex.org/W2156909104","https://openalex.org/W2158823144","https://openalex.org/W2998991762"],"related_works":["https://openalex.org/W7095478179","https://openalex.org/W198744195","https://openalex.org/W3125501814","https://openalex.org/W2515868713","https://openalex.org/W4299808782","https://openalex.org/W4220706633","https://openalex.org/W2561412020","https://openalex.org/W4388963696","https://openalex.org/W3196647676","https://openalex.org/W3176159406"],"abstract_inverted_index":{"This":[0],"is":[1,89,111,139],"a":[2,114,142,180,197,201,230],"design-science":[3],"paper":[4],"about":[5],"methods":[6],"for":[7,24,27,32,64,262],"explaining":[8,283],"data-driven":[9],"classi\ufb01cations":[10,285],"of":[11,49,53,61,117,124,144,167,192,216,269],"text":[12],"documents.":[13],"Document":[14,38],"classi\ufb01cation":[15,65,126,204,237,264,271],"has":[16],"widespread":[17],"applications,":[18],"such":[19,149,175,184],"as":[20,141,177,179,209],"with":[21,47,104,131,196,213],"web":[22,207],"pages":[23,208],"advertising,":[25],"emails":[26],"legal":[28],"discovery,":[29],"blog":[30],"entries":[31],"sentiment":[33],"analysis,":[34],"and":[35,71,127,252,254,273,292],"many":[36],"more.":[37],"data":[39,290],"are":[40],"characterized":[41],"by":[42,67,85],"very":[43,90],"high":[44,79],"dimensionality,":[45,80],"often":[46],"tens":[48],"thousands":[50],"to":[51,77,94,112,120,129,173,182,219,222,249,255,288],"millions":[52],"variables":[54],"(words).":[55],"Many":[56],"applications":[57],"require":[58],"human":[59],"understanding":[60,81],"the":[62,72,78,82,86,121,132,158,161,165,190,193,214,239,247,259,263,267,270,275],"reasons":[63,261],"decisions:":[66],"managers,":[68],"client-facing":[69],"employees,":[70],"technical":[73,134],"team.":[74],"Unfortunately,":[75],"due":[76],"decisions":[83],"made":[84],"document":[87,125,159,203],"classi\ufb01ers":[88],"difficult.":[91],"Previous":[92],"approaches":[93],"gain":[95],"insight":[96,257],"into":[97,258,266,274],"black-box":[98],"models":[99],"do":[100],"not":[101,221],"deal":[102],"well":[103,178],"high-dimensional":[105],"data.":[106],"Our":[107],"main":[108],"theoretical":[109],"contribution":[110],"de\ufb01ne":[113],"new":[115,194],"sort":[116],"explanation,":[118],"tailored":[119],"business":[122,276],"needs":[123],"able":[128],"cope":[130],"associated":[133],"constraints.":[135],"Speci\ufb01cally,":[136],"an":[137,171,185],"explanation":[138],"de\ufb01ned":[140],"set":[143,156],"words":[145,153],"(terms,":[146],"more":[147],"generally)":[148],"that":[150],"removing":[151],"all":[152],"within":[154],"this":[155],"from":[157,164,200],"changes":[160],"predicted":[162],"class":[163,166],"interest.":[168],"We":[169,188,228,279],"present":[170,229],"algorithm":[172],"\ufb01nd":[174],"explanations,":[176],"framework":[181],"assess":[183],"algorithm's":[186],"performance.":[187,294],"demonstrate":[189],"value":[191],"approach":[195],"case":[198],"study":[199],"real-world":[202],"task:":[205],"classifying":[206],"containing":[210],"adult":[211],"content,":[212],"goal":[215],"allowing":[217],"advertisers":[218],"choose":[220],"have":[223],"their":[224],"ads":[225],"appear":[226],"there.":[227],"further":[231],"empirical":[232],"demonstration":[233],"on":[234],"news-story":[235],"topic":[236],"using":[238],"20":[240],"Newsgroups":[241],"benchmark":[242],"dataset.":[243],"The":[244],"results":[245],"show":[246],"explanations":[248],"be":[250],"concise":[251],"document-speci\ufb01c,":[253],"provide":[256],"exact":[260],"decisions,":[265],"workings":[268],"models,":[272],"application":[277],"itself.":[278],"also":[280],"illustrate":[281],"how":[282],"documents'":[284],"can":[286],"help":[287],"improve":[289],"quality":[291],"model":[293]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}