{"id":"https://openalex.org/W2149978102","doi":"https://doi.org/10.1073/pnas.1018067108","title":"General purpose computer-assisted clustering and conceptualization","display_name":"General purpose computer-assisted clustering and conceptualization","publication_year":2011,"publication_date":"2011-02-03","ids":{"openalex":"https://openalex.org/W2149978102","doi":"https://doi.org/10.1073/pnas.1018067108","mag":"2149978102","pmid":"https://pubmed.ncbi.nlm.nih.gov/21292983"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.1018067108","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1018067108","pdf_url":"https://www.pnas.org/content/pnas/108/7/2643.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.pnas.org/content/pnas/108/7/2643.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090665793","display_name":"Justin Grimmer","orcid":"https://orcid.org/0000-0001-6642-9799"},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Grimmer","raw_affiliation_strings":["Department of Political Science, Stanford University, Encina Hall West, 616 Serra Street, Palo Alto, CA 94305; and"],"affiliations":[{"raw_affiliation_string":"Department of Political Science, Stanford University, Encina Hall West, 616 Serra Street, Palo Alto, CA 94305; and","institution_ids":["https://openalex.org/I1743320","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087421071","display_name":"Gary King","orcid":"https://orcid.org/0000-0002-5327-7631"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210098931","display_name":"Quantitative BioSciences","ror":"https://ror.org/010brsj79","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary King","raw_affiliation_strings":["Institute for Quantitative Social Science, Harvard University, 1737 Cambridge Street, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Institute for Quantitative Social Science, Harvard University, 1737 Cambridge Street, Cambridge, MA 02138","institution_ids":["https://openalex.org/I4210098931","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090665793"],"corresponding_institution_ids":["https://openalex.org/I1743320","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":18.0501,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.99279381,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"108","issue":"7","first_page":"2643","last_page":"2650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9970999956130981,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9950000047683716,"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/T11106","display_name":"Data Management and Algorithms","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7920767068862915},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.644246518611908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6046629548072815},{"id":"https://openalex.org/keywords/conceptualization","display_name":"Conceptualization","score":0.6013583540916443},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5893413424491882},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5363254547119141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.445831835269928},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4274471402168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4121183753013611},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3570246696472168},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33520036935806274},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11245778203010559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10704702138900757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920767068862915},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.644246518611908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6046629548072815},{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.6013583540916443},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5893413424491882},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5363254547119141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.445831835269928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4274471402168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4121183753013611},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3570246696472168},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33520036935806274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11245778203010559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10704702138900757},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1073/pnas.1018067108","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1018067108","pdf_url":"https://www.pnas.org/content/pnas/108/7/2643.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmid:21292983","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21292983","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":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":null},{"id":"pmh:oai:dash.harvard.edu:1/12724038","is_oa":true,"landing_page_url":"http://nrs.harvard.edu/urn-3:HUL.InstRepos:12724038","pdf_url":null,"source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:2161623","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3041127","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1073/pnas.1018067108","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1018067108","pdf_url":"https://www.pnas.org/content/pnas/108/7/2643.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2149978102.pdf","grobid_xml":"https://content.openalex.org/works/W2149978102.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W1485321296","https://openalex.org/W1510073064","https://openalex.org/W1516111018","https://openalex.org/W1532325895","https://openalex.org/W1666032117","https://openalex.org/W2002451181","https://openalex.org/W2004827391","https://openalex.org/W2038411619","https://openalex.org/W2039047078","https://openalex.org/W2046782908","https://openalex.org/W2082422522","https://openalex.org/W2107760749","https://openalex.org/W2107856676","https://openalex.org/W2127498532","https://openalex.org/W2134312057","https://openalex.org/W2139387599","https://openalex.org/W2139580617","https://openalex.org/W2157305458","https://openalex.org/W2169446650","https://openalex.org/W2171060319","https://openalex.org/W2293273145","https://openalex.org/W2295351501","https://openalex.org/W2314261489","https://openalex.org/W2491365176","https://openalex.org/W2942992487","https://openalex.org/W3092910336","https://openalex.org/W3101671285","https://openalex.org/W3125537406","https://openalex.org/W4213009331","https://openalex.org/W4285719527","https://openalex.org/W4301859188"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3010198599","https://openalex.org/W2075832457","https://openalex.org/W2614500124"],"abstract_inverted_index":{"We":[0,84,168],"develop":[1,85],"a":[2,39,61,73,86,99,118],"computer-assisted":[3,157],"method":[4],"for":[5,72],"the":[6,12,23,53],"discovery":[7,178],"of":[8,14,18,22,28,64,89,105,113,179],"insightful":[9,133,177],"conceptualizations,":[10],"in":[11,32,66,144,164],"form":[13],"clusterings":[15],"(i.e.,":[16],"partitions)":[17],"input":[19],"objects.":[20],"Each":[21],"numerous":[24],"fully":[25,189],"automated":[26,190],"methods":[27,96],"cluster":[29,94],"analysis":[30,95],"proposed":[31],"statistics,":[33],"computer":[34],"science,":[35],"and":[36,78,116,122,126,150,176],"biology":[37],"optimize":[38],"different":[40],"objective":[41],"function.":[42],"Almost":[43],"all":[44,92],"are":[45],"well":[46],"defined,":[47],"but":[48],"how":[49],"to":[50,98,120,141,160],"determine":[51],"before":[52],"fact":[54],"which":[55],"one,":[56],"if":[57,80],"any,":[58],"will":[59],"partition":[60],"given":[62,74,100],"set":[63],"objects":[65],"an":[67],"\"insightful\"":[68],"or":[69,129,132,186],"\"useful\"":[70],"way":[71],"user":[75,119],"is":[76,139],"unknown":[77],"difficult,":[79],"not":[81],"logically":[82],"impossible.":[83],"metric":[87],"space":[88],"partitions":[90],"from":[91],"existing":[93,114,188],"applied":[97],"dataset":[101],"(along":[102],"with":[103,124],"millions":[104],"other":[106],"solutions":[107],"we":[108,148],"add":[109],"based":[110],"on":[111],"combinations":[112],"clusterings)":[115],"enable":[117],"explore":[121],"interact":[123],"it":[125,138],"quickly":[127],"reveal":[128],"prompt":[130],"useful":[131,180],"conceptualizations.":[134],"In":[135],"addition,":[136],"although":[137],"uncommon":[140],"do":[142],"so":[143],"unsupervised":[145],"learning":[146],"problems,":[147],"offer":[149],"implement":[151],"evaluation":[152],"designs":[153],"that":[154,170],"make":[155],"our":[156,171],"approach":[158,172],"vulnerable":[159],"being":[161],"proven":[162],"suboptimal":[163],"specific":[165],"data":[166],"types.":[167],"demonstrate":[169],"facilitates":[173],"more":[174],"efficient":[175],"information":[181],"than":[182],"expert":[183],"human":[184],"coders":[185],"many":[187],"methods.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}