{"id":"https://openalex.org/W1953585660","doi":"https://doi.org/10.1162/coli_a_00230","title":"Evaluation Methods for Statistically Dependent Text","display_name":"Evaluation Methods for Statistically Dependent Text","publication_year":2015,"publication_date":"2015-07-20","ids":{"openalex":"https://openalex.org/W1953585660","doi":"https://doi.org/10.1162/coli_a_00230","mag":"1953585660"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00230","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00230","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00230","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041251183","display_name":"Sarvnaz Karimi","orcid":"https://orcid.org/0000-0002-4927-3937"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarvnaz Karimi","raw_affiliation_strings":["CSIRO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014017635","display_name":"Jie Yin","orcid":"https://orcid.org/0000-0002-2063-8437"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Yin","raw_affiliation_strings":["CSIRO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040921393","display_name":"Jiri Baum","orcid":null},"institutions":[{"id":"https://openalex.org/I97750245","display_name":"Software (Spain)","ror":"https://ror.org/02ethns06","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210087817","https://openalex.org/I97750245"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jiri Baum","raw_affiliation_strings":["Sabik Software Solutions","Sabik Software Solutions#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sabik Software Solutions","institution_ids":[]},{"raw_affiliation_string":"Sabik Software Solutions#TAB#","institution_ids":["https://openalex.org/I97750245"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5285,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88523764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"41","issue":"3","first_page":"539","last_page":"548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9952999949455261,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9952999949455261,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7589166760444641},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7385764122009277},{"id":"https://openalex.org/keywords/microblogging","display_name":"Microblogging","score":0.7007430195808411},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5664834976196289},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5341448187828064},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.46045970916748047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2846214473247528},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1781296730041504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589166760444641},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7385764122009277},{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.7007430195808411},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5664834976196289},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5341448187828064},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.46045970916748047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2846214473247528},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1781296730041504},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00230","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00230","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00230","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:55a913e1b30c4831b16e22819105daf3","is_oa":true,"landing_page_url":"https://doaj.org/article/55a913e1b30c4831b16e22819105daf3","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 41, Iss 3 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00230","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00230","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00230","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1953585660.pdf","grobid_xml":"https://content.openalex.org/works/W1953585660.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W50740790","https://openalex.org/W1498924130","https://openalex.org/W1517808374","https://openalex.org/W1968194983","https://openalex.org/W1976323204","https://openalex.org/W1981552604","https://openalex.org/W1981780459","https://openalex.org/W2004230795","https://openalex.org/W2008654787","https://openalex.org/W2019678805","https://openalex.org/W2053968437","https://openalex.org/W2057822527","https://openalex.org/W2066090712","https://openalex.org/W2096850081","https://openalex.org/W2113125055","https://openalex.org/W2145131124","https://openalex.org/W2153635508","https://openalex.org/W3104887532"],"related_works":["https://openalex.org/W2728430307","https://openalex.org/W2107786128","https://openalex.org/W2053241453","https://openalex.org/W2153980712","https://openalex.org/W2537388533","https://openalex.org/W2978974359","https://openalex.org/W2036556872","https://openalex.org/W2021183651","https://openalex.org/W2017590198","https://openalex.org/W2353191283"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"many":[3],"studies":[4,24,69],"have":[5,25],"been":[6],"published":[7,103],"on":[8,79],"data":[9,58,81,140],"collected":[10,82],"from":[11],"social":[12,105],"media,":[13,106],"especially":[14],"microblogs":[15],"such":[16,38,62],"as":[17,63],"Twitter.":[18],"However,":[19],"rather":[20],"few":[21],"of":[22,37,59,67,99],"these":[23,68],"considered":[26],"evaluation":[27,122],"methodologies":[28],"that":[29,87,93,124],"take":[30],"into":[31],"account":[32],"the":[33,42,52,96,100],"statistically":[34],"dependent":[35],"nature":[36],"data,":[39],"which":[40,142],"breaks":[41],"theoretical":[43],"conditions":[44,144],"for":[45,57,137,141],"using":[46,55,73],"cross-validation.":[47,76],"Despite":[48],"concerns":[49,136],"raised":[50],"in":[51,104,111,114,130],"past":[53],"about":[54],"cross-validation":[56,108],"similar":[60,143],"characteristics,":[61],"time":[64],"series,":[65],"some":[66],"evaluate":[70],"their":[71],"work":[72,133],"standard":[74,107],"k-fold":[75],"Through":[77],"experiments":[78],"Twitter":[80],"during":[83],"a":[84,115],"two-year":[85],"period":[86],"includes":[88],"disastrous":[89],"events,":[90],"we":[91],"show":[92],"by":[94],"ignoring":[95],"statistical":[97,128],"dependence":[98,129],"text":[101],"messages":[102],"can":[109],"result":[110],"misleading":[112],"conclusions":[113],"machine":[116],"learning":[117],"task.":[118],"We":[119],"explore":[120],"alternative":[121],"methods":[123],"explicitly":[125],"deal":[126],"with":[127],"text.":[131],"Our":[132],"also":[134],"raises":[135],"any":[138],"other":[139],"might":[145],"hold.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}
