{"id":"https://openalex.org/W4381435402","doi":"https://doi.org/10.1162/coli_a_00487","title":"Capturing Fine-Grained Regional Differences in Language Use through Voting Precinct Embeddings","display_name":"Capturing Fine-Grained Regional Differences in Language Use through Voting Precinct Embeddings","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4381435402","doi":"https://doi.org/10.1162/coli_a_00487"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00487","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00487","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00487/2133665/coli_a_00487.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00487/2133665/coli_a_00487.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002246476","display_name":"Alex Rosenfeld","orcid":"https://orcid.org/0000-0001-6140-7355"},"institutions":[{"id":"https://openalex.org/I114662689","display_name":"Leidos (United States)","ror":"https://ror.org/012cvds63","country_code":"US","type":"company","lineage":["https://openalex.org/I114662689"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alex Rosenfeld","raw_affiliation_strings":["Leidos, Innovations Center. alexbrosenfeld@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leidos, Innovations Center. alexbrosenfeld@gmail.com","institution_ids":["https://openalex.org/I114662689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041412717","display_name":"Lars Hinrichs","orcid":"https://orcid.org/0000-0003-3679-1927"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lars Hinrichs","raw_affiliation_strings":["The University of Texas at Austin, Department of English. TxE@utexas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Department of English. TxE@utexas.edu","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002246476"],"corresponding_institution_ids":["https://openalex.org/I114662689"],"apc_list":null,"apc_paid":null,"fwci":1.7561,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86232358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"49","issue":"4","first_page":"883","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10265","display_name":"Multilingual Education and Policy","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.97079998254776,"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/variation","display_name":"Variation (astronomy)","score":0.7837050557136536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7368135452270508},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.6130942702293396},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5478231906890869},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5463221669197083},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5434924960136414},{"id":"https://openalex.org/keywords/precinct","display_name":"Precinct","score":0.5372275114059448},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5192946791648865},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4801163673400879},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4765875041484833},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.47389450669288635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41269195079803467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3751574754714966},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3341432809829712},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.32151785492897034},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1636669933795929},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.14034438133239746},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09637871384620667}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7837050557136536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368135452270508},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.6130942702293396},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5478231906890869},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5463221669197083},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5434924960136414},{"id":"https://openalex.org/C2776442119","wikidata":"https://www.wikidata.org/wiki/Q92785642","display_name":"Precinct","level":2,"score":0.5372275114059448},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5192946791648865},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4801163673400879},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4765875041484833},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.47389450669288635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41269195079803467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3751574754714966},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3341432809829712},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.32151785492897034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1636669933795929},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14034438133239746},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09637871384620667},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00487","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00487","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00487/2133665/coli_a_00487.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2220b65351ac435591a80954ef22344e","is_oa":true,"landing_page_url":"https://doaj.org/article/2220b65351ac435591a80954ef22344e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 49, Iss 4 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00487","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00487","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00487/2133665/coli_a_00487.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4381435402.pdf"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W55848811","https://openalex.org/W91819055","https://openalex.org/W168564468","https://openalex.org/W609272014","https://openalex.org/W1495507141","https://openalex.org/W1503259811","https://openalex.org/W1504725289","https://openalex.org/W1537581591","https://openalex.org/W1607035479","https://openalex.org/W1796112755","https://openalex.org/W1979839410","https://openalex.org/W1990236680","https://openalex.org/W1993477690","https://openalex.org/W2013416277","https://openalex.org/W2020170780","https://openalex.org/W2045980827","https://openalex.org/W2052611179","https://openalex.org/W2078129874","https://openalex.org/W2095688790","https://openalex.org/W2097934124","https://openalex.org/W2100314787","https://openalex.org/W2102637390","https://openalex.org/W2107798163","https://openalex.org/W2127681423","https://openalex.org/W2146792999","https://openalex.org/W2150333745","https://openalex.org/W2155219921","https://openalex.org/W2160523162","https://openalex.org/W2186717077","https://openalex.org/W2186721685","https://openalex.org/W2187089797","https://openalex.org/W2234751941","https://openalex.org/W2251157848","https://openalex.org/W2264054297","https://openalex.org/W2292415828","https://openalex.org/W2314698409","https://openalex.org/W2315029193","https://openalex.org/W2317845990","https://openalex.org/W2325868445","https://openalex.org/W2328884754","https://openalex.org/W2331570300","https://openalex.org/W2334869126","https://openalex.org/W2519672670","https://openalex.org/W2604272474","https://openalex.org/W2747812981","https://openalex.org/W2750747353","https://openalex.org/W2795566627","https://openalex.org/W2804830075","https://openalex.org/W2807302113","https://openalex.org/W2810140910","https://openalex.org/W2889983522","https://openalex.org/W2898729163","https://openalex.org/W2963099212","https://openalex.org/W2963666326","https://openalex.org/W3099853061","https://openalex.org/W3113924821","https://openalex.org/W3157570421","https://openalex.org/W3174459789","https://openalex.org/W4206472724","https://openalex.org/W4232489687","https://openalex.org/W4232590155","https://openalex.org/W4235442395","https://openalex.org/W4245325624","https://openalex.org/W4246811648","https://openalex.org/W6603772380","https://openalex.org/W6629555621","https://openalex.org/W6633117799","https://openalex.org/W6634938555","https://openalex.org/W6674688028","https://openalex.org/W6679775712","https://openalex.org/W6681267133","https://openalex.org/W6681685464","https://openalex.org/W6682691769","https://openalex.org/W6686441926","https://openalex.org/W6686851947","https://openalex.org/W6704588003","https://openalex.org/W6793830562"],"related_works":["https://openalex.org/W2091493000","https://openalex.org/W2480508178","https://openalex.org/W3165175181","https://openalex.org/W4249918192","https://openalex.org/W2178651580","https://openalex.org/W2625316527","https://openalex.org/W2906868007","https://openalex.org/W4309351812","https://openalex.org/W1972594981","https://openalex.org/W2045966063"],"abstract_inverted_index":{"Abstract":[0],"Linguistic":[1],"variation":[2,153],"across":[3,154],"a":[4,60,135,186,190,204,241,247,259,267],"region":[5,14],"of":[6,90,107,209,249],"interest":[7],"can":[8,85,173,188,206],"be":[9,174,219],"captured":[10],"by":[11,222],"partitioning":[12],"the":[13,105,120,171,233],"into":[15],"areas":[16,58,117,127],"and":[17,224,262],"using":[18,244,284],"social":[19,48,130],"media":[20,49,131],"data":[21,50,121],"to":[22,44,63,80,176,195,258,266,274],"train":[23],"embeddings":[24,172,245],"that":[25,46,76,119,139,167,196,256],"represent":[26],"language":[27,72,91,113],"use":[28,114],"in":[29,53,71,115],"those":[30,264],"areas.":[31],"Recent":[32],"work":[33],"has":[34],"focused":[35],"on":[36,151],"larger":[37,57],"areas,":[38,83],"such":[39,67],"as":[40,68,156,246],"cities":[41],"or":[42],"counties,":[43],"ensure":[45],"enough":[47],"is":[51,78,118,158,230],"available":[52],"each":[54],"area,":[55],"but":[56],"have":[59],"limited":[61],"ability":[62],"find":[64],"fine-grained":[65],"distinctions,":[66],"intracity":[69],"differences":[70],"use.":[73],"We":[74,93,133,149,161,235],"demonstrate":[75],"it":[77,157],"possible":[79],"embed":[81,94],"smaller":[82],"which":[84,97,144],"provide":[86],"higher":[87],"resolution":[88],"analyses":[89],"variation.":[92,179],"voting":[95],"precincts,":[96],"are":[98],"tiny,":[99],"evenly":[100],"sized":[101],"political":[102],"divisions":[103],"for":[104,243,281],"administration":[106],"elections.":[108],"The":[109,180,198],"issue":[110],"with":[111,125,142,240],"modeling":[112],"small":[116],"becomes":[122],"incredibly":[123],"sparse,":[124],"many":[126],"having":[128],"scant":[129],"data.":[132],"propose":[134],"novel":[136,164],"embedding":[137,216],"approach":[138],"alternates":[140],"training":[141],"smoothing,":[143],"mitigates":[145],"these":[146],"sparsity":[147],"issues.":[148],"focus":[150],"linguistic":[152,178,268,275],"Texas":[155],"relatively":[159],"understudied.":[160],"develop":[162],"two":[163],"quantitative":[165],"evaluations":[166,213],"measure":[168,225],"how":[169,184,202,215,226],"well":[170,185,203],"used":[175,220],"capture":[177],"first":[181],"evaluation":[182,200,239],"measures":[183,201],"model":[187,205],"map":[189,207],"dialect":[191],"given":[192],"terms":[193],"specific":[194],"dialect.":[197],"second":[199,238],"preference":[208],"lexical":[210],"variants.":[211],"These":[212],"show":[214],"models":[217],"could":[218],"directly":[221],"sociolinguists":[223],"much":[227],"sociolinguistic":[228],"information":[229],"contained":[231],"within":[232],"embeddings.":[234,285],"complement":[236],"this":[237],"methodology":[242],"kind":[248],"genetic":[250],"code":[251],"where":[252],"we":[253,278],"identify":[254],"\u201cgenes\u201d":[255,265],"correspond":[257],"sociological":[260,272],"variable":[261],"connect":[263],"phenomenon":[269],"thereby":[270],"connecting":[271],"phenomena":[273],"ones.":[276],"Finally,":[277],"explore":[279],"approaches":[280],"inferring":[282],"isoglosses":[283]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}