{"id":"https://openalex.org/W2067145123","doi":"https://doi.org/10.1145/2644866.2644870","title":"Humanist-centric tools for big data","display_name":"Humanist-centric tools for big data","publication_year":2014,"publication_date":"2014-09-16","ids":{"openalex":"https://openalex.org/W2067145123","doi":"https://doi.org/10.1145/2644866.2644870","mag":"2067145123"},"language":"en","primary_location":{"id":"doi:10.1145/2644866.2644870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","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/A5032027019","display_name":"Patrick Schmitz","orcid":"https://orcid.org/0000-0003-0659-6880"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrick Schmitz","raw_affiliation_strings":["University of California at Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032090044","display_name":"Laurie Pearce","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurie Pearce","raw_affiliation_strings":["University of California at Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032027019"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12974761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9884999990463257,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8014721870422363},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5777459740638733},{"id":"https://openalex.org/keywords/prosopography","display_name":"Prosopography","score":0.5581261515617371},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47914522886276245},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.44822201132774353},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4233686327934265},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.42289280891418457},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4144074320793152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3752654790878296},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3700900077819824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32915711402893066},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15673348307609558},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10973668098449707},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10464844107627869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014721870422363},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5777459740638733},{"id":"https://openalex.org/C134683919","wikidata":"https://www.wikidata.org/wiki/Q783287","display_name":"Prosopography","level":2,"score":0.5581261515617371},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47914522886276245},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.44822201132774353},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4233686327934265},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42289280891418457},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4144074320793152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752654790878296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3700900077819824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32915711402893066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15673348307609558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10973668098449707},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10464844107627869},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C195244886","wikidata":"https://www.wikidata.org/wiki/Q41493","display_name":"Ancient history","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2644866.2644870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4677551336","display_name":null,"funder_award_id":"HD-51041-10","funder_id":"https://openalex.org/F4320306100","funder_display_name":"National Endowment for the Humanities"}],"funders":[{"id":"https://openalex.org/F4320306100","display_name":"National Endowment for the Humanities","ror":"https://ror.org/02vdm1p28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W105330602","https://openalex.org/W653092284","https://openalex.org/W1548235094","https://openalex.org/W1998309189","https://openalex.org/W2001291669","https://openalex.org/W2040120915","https://openalex.org/W2078645326","https://openalex.org/W2135415614","https://openalex.org/W2140945425","https://openalex.org/W2885597964","https://openalex.org/W2946664639","https://openalex.org/W6670147936"],"related_works":["https://openalex.org/W2767450342","https://openalex.org/W3143937874","https://openalex.org/W4295151157","https://openalex.org/W2483038269","https://openalex.org/W2200241032","https://openalex.org/W2819137623","https://openalex.org/W4239501324","https://openalex.org/W4299509257","https://openalex.org/W3127069067","https://openalex.org/W2591037847"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4,144,202],"Berkeley":[5],"Prosopography":[6,32],"Services":[7],"(BPS),":[8],"a":[9,86,103,212],"new":[10],"set":[11],"of":[12,19,23,29,36,47,89,106,122,147,189,198,208,215],"tools":[13,194,210],"for":[14,73,100,129],"prosopography":[15],"-":[16,26],"the":[17,40,45,48,52,90,119,145,148,193,206,209],"identification":[18],"individuals":[20],"and":[21,56,79,96,115,133,171,175,201],"study":[22,196],"their":[24],"interactions":[25],"in":[27,39,152,168],"support":[28],"humanities":[30],"research.":[31],"is":[33,64,85],"an":[34,186],"example":[35],"\"big":[37],"data\"":[38],"humanities,":[41],"characterized":[42],"not":[43],"by":[44,51,94,140],"size":[46],"datasets,":[49],"but":[50],"way":[53],"that":[54],"computational":[55],"data-driven":[57],"methods":[58],"can":[59],"transform":[60],"scholarly":[61],"workflows.":[62],"BPS":[63,82,120,149],"based":[65],"upon":[66],"re-usable":[67],"infrastructure,":[68],"supporting":[69],"generalized":[70],"web":[71],"services":[72],"corpus":[74],"management,":[75],"social":[76],"network":[77],"analysis,":[78,132],"visualization.":[80],"The":[81],"disambiguation":[83],"model":[84,111,121,137,151],"formal":[87],"implementation":[88],"traditional":[91],"heuristics":[92],"used":[93],"humanists,":[95],"supports":[97,112],"plug-in":[98],"rules":[99,125],"adaptation":[101],"to":[102,126,161,165,172,195,204,211],"wide":[104],"range":[105,214],"domain":[107],"corpora.":[108,216],"A":[109],"workspace":[110],"exploratory":[113],"research":[114],"collaboration.":[116],"We":[117,143,184],"contrast":[118],"configurable":[123],"heuristic":[124],"other":[127],"approaches":[128],"automated":[130,163],"text":[131],"explain":[134],"how":[135],"our":[136],"facilitates":[138],"interpretation":[139],"humanist":[141],"researchers.":[142],"significance":[146],"assertion":[150],"which":[153],"researchers":[154],"assert":[155],"conclusions":[156],"or":[157],"possibilities,":[158],"allowing":[159],"them":[160],"override":[162],"inference,":[164],"explore":[166],"ideas":[167],"what-if":[169],"scenarios,":[170],"formally":[173],"publish":[174],"subscribe-to":[176],"asserted":[177],"annotations":[178],"among":[179],"colleagues,":[180],"and/or":[181],"with":[182],"students.":[183],"present":[185],"initial":[187],"evaluation":[188],"researchers'":[190],"experience":[191],"using":[192],"corpora":[197],"cuneiform":[199],"tablets,":[200],"plans":[203],"expand":[205],"application":[207],"broader":[213]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}