{"id":"https://openalex.org/W4399913979","doi":"https://doi.org/10.1093/llc/fqae029","title":"Language-based machine perception: linguistic perspectives on the compilation of captioning datasets","display_name":"Language-based machine perception: linguistic perspectives on the compilation of captioning datasets","publication_year":2024,"publication_date":"2024-06-21","ids":{"openalex":"https://openalex.org/W4399913979","doi":"https://doi.org/10.1093/llc/fqae029"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqae029","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1093/llc/fqae029","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqae029/58307413/fqae029.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqae029/58307413/fqae029.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033978141","display_name":"Laura Hekanaho","orcid":"https://orcid.org/0000-0002-1064-6871"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Laura Hekanaho","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085115508","display_name":"Maija Hirvonen","orcid":"https://orcid.org/0000-0002-7631-1310"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Maija Hirvonen","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University , Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033978141"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":{"value":2522,"currency":"GBP","value_usd":3093},"apc_paid":null,"fwci":0.2622,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50211285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"39","issue":"3","first_page":"864","last_page":"883"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.7905124425888062},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.7888438701629639},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7420535087585449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5373894572257996},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.5327510833740234},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5115976929664612},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4943978786468506},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4858393371105194},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.4614803194999695},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4192872941493988},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41367560625076294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120345115661621},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3540303707122803},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2506909668445587},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12481245398521423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905124425888062},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.7888438701629639},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7420535087585449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5373894572257996},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.5327510833740234},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5115976929664612},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4943978786468506},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4858393371105194},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.4614803194999695},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4192872941493988},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41367560625076294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120345115661621},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3540303707122803},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2506909668445587},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12481245398521423},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/llc/fqae029","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1093/llc/fqae029","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqae029/58307413/fqae029.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/210614","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/210614","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/llc/fqae029","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1093/llc/fqae029","pdf_url":"https://academic.oup.com/dsh/advance-article-pdf/doi/10.1093/llc/fqae029/58307413/fqae029.pdf","source":{"id":"https://openalex.org/S2734814886","display_name":"Digital Scholarship in the Humanities","issn_l":"2055-7671","issn":["2055-7671","2055-768X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Scholarship in the Humanities","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322861","display_name":"Emil Aaltosen S\u00e4\u00e4ti\u00f6","ror":"https://ror.org/005rt3g54"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399913979.pdf"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W152618306","https://openalex.org/W172918197","https://openalex.org/W261871827","https://openalex.org/W594548793","https://openalex.org/W595267711","https://openalex.org/W608574129","https://openalex.org/W612101053","https://openalex.org/W1483377176","https://openalex.org/W1506491340","https://openalex.org/W1532520101","https://openalex.org/W1536041129","https://openalex.org/W1550708636","https://openalex.org/W1581036748","https://openalex.org/W1861492603","https://openalex.org/W1978703882","https://openalex.org/W1996650435","https://openalex.org/W2042627297","https://openalex.org/W2086220385","https://openalex.org/W2089821026","https://openalex.org/W2119268328","https://openalex.org/W2141869176","https://openalex.org/W2150612552","https://openalex.org/W2158428778","https://openalex.org/W2181476823","https://openalex.org/W2274640565","https://openalex.org/W2277195237","https://openalex.org/W2285144430","https://openalex.org/W2298263529","https://openalex.org/W2337252826","https://openalex.org/W2519564115","https://openalex.org/W2793705218","https://openalex.org/W2883336577","https://openalex.org/W2911801932","https://openalex.org/W3046420925","https://openalex.org/W3087065520","https://openalex.org/W3094252162","https://openalex.org/W3095670406","https://openalex.org/W3106859150","https://openalex.org/W3110019360","https://openalex.org/W3171716568","https://openalex.org/W3172707490","https://openalex.org/W3181414820","https://openalex.org/W3183248212","https://openalex.org/W3210445109","https://openalex.org/W3216130706","https://openalex.org/W4206459472","https://openalex.org/W4211092749","https://openalex.org/W4213054092","https://openalex.org/W4243183569","https://openalex.org/W4248420672","https://openalex.org/W4252258876","https://openalex.org/W4253118155","https://openalex.org/W4254051021","https://openalex.org/W4280567182","https://openalex.org/W4300610252","https://openalex.org/W4300858098","https://openalex.org/W4312956563","https://openalex.org/W4313152851","https://openalex.org/W4362235778","https://openalex.org/W6606239278","https://openalex.org/W6631821887","https://openalex.org/W6679959949","https://openalex.org/W6685467371","https://openalex.org/W6796516838","https://openalex.org/W6845235097"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W1687432146","https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W1591874556","https://openalex.org/W3110264473","https://openalex.org/W2775506363","https://openalex.org/W2185608106","https://openalex.org/W3046258185","https://openalex.org/W4366988985"],"abstract_inverted_index":{"Abstract":[0],"Over":[1],"the":[2,71,82,87,92,122,125,129,135,140,148,159,168,182,193,200,219,234,237],"last":[3],"decade,":[4],"a":[5,30,64,100,109],"plethora":[6],"of":[7,47,74,91,111,124,134,147,161,181,195,199,204,209,221,236],"training":[8,49],"datasets":[9,50,76,227],"have":[10,165],"been":[11],"compiled":[12],"for":[13],"use":[14,203],"in":[15,20,39,52,80,158,167],"language-based":[16],"machine":[17],"perception":[18],"and":[19,56,89,97,131,179,184,207,224],"human-centered":[21],"AI,":[22],"alongside":[23],"research":[24],"regarding":[25],"their":[26,60],"compilation":[27,61,220],"methods.":[28],"From":[29],"primarily":[31],"linguistic":[32,83],"perspective,":[33],"we":[34,43,68,104,127,170,191,217],"add":[35],"to":[36,164],"these":[37],"studies":[38],"two":[40],"ways.":[41],"First,":[42],"provide":[44],"an":[45,78,144],"overview":[46],"sixty-six":[48],"used":[51],"automatic":[53],"image,":[54],"video,":[55],"audio":[57],"captioning,":[58],"examining":[59],"methods":[62],"with":[63,77,108,214],"metadata":[65],"analysis.":[66],"Second,":[67],"delve":[69],"into":[70],"annotation":[72],"process":[73],"crowdsourced":[75,225],"interest":[79],"understanding":[81],"factors":[84,232],"that":[85,119,142,155],"affect":[86],"form":[88],"content":[90,102],"captions,":[93],"such":[94],"as":[95,137,139],"contextualization":[96],"perspectivation.":[98],"With":[99],"qualitative":[101],"analysis,":[103],"examine":[105],"annotator":[106],"instructions":[107,162],"selection":[110],"eleven":[112],"datasets.":[113,238],"Drawing":[114],"from":[115,228],"various":[116,173,229],"theoretical":[117],"frameworks":[118],"help":[120],"assess":[121,218],"effectiveness":[123],"instructions,":[126,136,183],"discuss":[128],"visual":[130],"textual":[132],"presentation":[133],"well":[138],"perspective-guidance":[141],"is":[143],"essential":[145],"part":[146],"language":[149,210],"instructions.":[150],"While":[151],"our":[152],"analysis":[153],"indicates":[154],"some":[156],"standards":[157],"formulation":[160],"seem":[163],"formed":[166],"field,":[169],"also":[171],"identified":[172],"reoccurring":[174],"issues":[175],"potentially":[176],"hindering":[177],"readability":[178],"comprehensibility":[180],"therefore,":[185],"caption":[186],"quality.":[187],"To":[188],"enhance":[189],"readability,":[190],"emphasize":[192],"importance":[194],"text":[196],"structure,":[197],"organization":[198],"information,":[201],"consistent":[202],"typographical":[205],"cues,":[206],"clarity":[208],"use.":[211],"Last,":[212],"engaging":[213],"previous":[215],"research,":[216],"both":[222],"web-sourced":[223],"captioning":[226],"perspectives,":[230],"discussing":[231],"affecting":[233],"diversity":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
