{"id":"https://openalex.org/W4319314361","doi":"https://doi.org/10.1017/s1351324922000535","title":"How to do human evaluation: A brief introduction to user studies in NLP","display_name":"How to do human evaluation: A brief introduction to user studies in NLP","publication_year":2023,"publication_date":"2023-02-06","ids":{"openalex":"https://openalex.org/W4319314361","doi":"https://doi.org/10.1017/s1351324922000535"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324922000535","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000535","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/85A5D9550233DFC3CF356DD7041E3306/S1351324922000535a.pdf/div-class-title-how-to-do-human-evaluation-a-brief-introduction-to-user-studies-in-nlp-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/85A5D9550233DFC3CF356DD7041E3306/S1351324922000535a.pdf/div-class-title-how-to-do-human-evaluation-a-brief-introduction-to-user-studies-in-nlp-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073257797","display_name":"Hendrik Schuff","orcid":"https://orcid.org/0000-0003-0523-4538"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hendrik Schuff","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany","Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]},{"raw_affiliation_string":"Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034325503","display_name":"Lindsey Vanderlyn","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lindsey Vanderlyn","raw_affiliation_strings":["Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055589412","display_name":"Heike Adel","orcid":"https://orcid.org/0000-0003-2787-0084"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heike Adel","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Maschinelle Sprachverarbeitung, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073257797"],"corresponding_institution_ids":["https://openalex.org/I100066346","https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":3.9544,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94758503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"5","first_page":"1199","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9934999942779541,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9876000285148621,"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":0.8747909069061279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6970096230506897},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6902023553848267},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6254177689552307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5792227983474731},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.545773983001709},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.520204484462738},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.44012635946273804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37755346298217773},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12760639190673828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8747909069061279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6970096230506897},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6902023553848267},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6254177689552307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5792227983474731},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.545773983001709},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.520204484462738},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.44012635946273804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37755346298217773},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12760639190673828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324922000535","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000535","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/85A5D9550233DFC3CF356DD7041E3306/S1351324922000535a.pdf/div-class-title-how-to-do-human-evaluation-a-brief-introduction-to-user-studies-in-nlp-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1017/s1351324922000535","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324922000535","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/85A5D9550233DFC3CF356DD7041E3306/S1351324922000535a.pdf/div-class-title-how-to-do-human-evaluation-a-brief-introduction-to-user-studies-in-nlp-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319314361.pdf"},"referenced_works_count":104,"referenced_works":["https://openalex.org/W62106667","https://openalex.org/W112288907","https://openalex.org/W619377242","https://openalex.org/W1489525520","https://openalex.org/W1520857482","https://openalex.org/W1762172548","https://openalex.org/W1763968285","https://openalex.org/W1897887843","https://openalex.org/W1938091964","https://openalex.org/W1979290264","https://openalex.org/W1984486655","https://openalex.org/W2003572185","https://openalex.org/W2013784666","https://openalex.org/W2015629112","https://openalex.org/W2029445248","https://openalex.org/W2041812559","https://openalex.org/W2050453477","https://openalex.org/W2056099611","https://openalex.org/W2057125152","https://openalex.org/W2059700429","https://openalex.org/W2072500831","https://openalex.org/W2075861156","https://openalex.org/W2079511794","https://openalex.org/W2087484885","https://openalex.org/W2088693609","https://openalex.org/W2100175927","https://openalex.org/W2106568252","https://openalex.org/W2107026277","https://openalex.org/W2109272923","https://openalex.org/W2116323796","https://openalex.org/W2119555207","https://openalex.org/W2136589719","https://openalex.org/W2141708418","https://openalex.org/W2142225512","https://openalex.org/W2142510360","https://openalex.org/W2147192413","https://openalex.org/W2148504207","https://openalex.org/W2154686027","https://openalex.org/W2157289187","https://openalex.org/W2158905336","https://openalex.org/W2164368909","https://openalex.org/W2182894058","https://openalex.org/W2184858235","https://openalex.org/W2249595199","https://openalex.org/W2251927615","https://openalex.org/W2252166243","https://openalex.org/W2264788300","https://openalex.org/W2279242506","https://openalex.org/W2522467290","https://openalex.org/W2576021677","https://openalex.org/W2591778563","https://openalex.org/W2612675303","https://openalex.org/W2613253298","https://openalex.org/W2742139733","https://openalex.org/W2775677125","https://openalex.org/W2787894218","https://openalex.org/W2793081411","https://openalex.org/W2798935874","https://openalex.org/W2801490189","https://openalex.org/W2801702920","https://openalex.org/W2804878416","https://openalex.org/W2897383465","https://openalex.org/W2901066322","https://openalex.org/W2928662674","https://openalex.org/W2944870985","https://openalex.org/W2962202409","https://openalex.org/W2963466651","https://openalex.org/W2963903950","https://openalex.org/W2967220154","https://openalex.org/W2968893733","https://openalex.org/W2988818867","https://openalex.org/W2990318625","https://openalex.org/W2992347006","https://openalex.org/W2996614149","https://openalex.org/W3023690688","https://openalex.org/W3035408261","https://openalex.org/W3040026531","https://openalex.org/W3098683121","https://openalex.org/W3101960104","https://openalex.org/W3102195370","https://openalex.org/W3106229690","https://openalex.org/W3107855336","https://openalex.org/W3109862485","https://openalex.org/W3110131742","https://openalex.org/W3112717819","https://openalex.org/W3156686659","https://openalex.org/W3156757420","https://openalex.org/W3161412941","https://openalex.org/W3199469083","https://openalex.org/W3213713237","https://openalex.org/W4230773990","https://openalex.org/W4240424693","https://openalex.org/W4245383073","https://openalex.org/W4249303080","https://openalex.org/W4250626195","https://openalex.org/W4283157866","https://openalex.org/W4301970156","https://openalex.org/W4302030570","https://openalex.org/W6653893718","https://openalex.org/W6683268542","https://openalex.org/W6686308954","https://openalex.org/W6693132809","https://openalex.org/W6769851266","https://openalex.org/W7070422636"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W1503094549","https://openalex.org/W4384486036","https://openalex.org/W2775554247","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"Abstract":[0],"Many":[1],"research":[2],"topics":[3],"in":[4,71,126],"natural":[5],"language":[6],"processing":[7],"(NLP),":[8],"such":[9],"as":[10],"explanation":[11],"generation,":[12],"dialog":[13],"modeling,":[14],"or":[15,27],"machine":[16],"translation,":[17],"require":[18],"evaluation":[19,138,155],"that":[20,140],"goes":[21],"beyond":[22],"standard":[23],"metrics":[24],"like":[25],"accuracy":[26],"F":[28],"1":[29],"score":[30],"toward":[31],"a":[32],"more":[33],"human-centered":[34],"approach.":[35],"Therefore,":[36],"understanding":[37],"how":[38],"to":[39,63,97,115,132,143,157],"design":[40,91],"user":[41,56,87,124],"studies":[42,57,88,125],"becomes":[43],"increasingly":[44],"important.":[45],"However,":[46],"few":[47],"comprehensive":[48],"resources":[49],"exist":[50],"on":[51],"planning,":[52],"conducting,":[53],"and":[54,89,92,100,113,128,137,164],"evaluating":[55],"for":[58,66,117],"NLP,":[59,127],"making":[60],"it":[61],"hard":[62],"get":[64],"started":[65],"researchers":[67],"without":[68],"prior":[69],"experience":[70],"the":[72,82,121,144,159],"field":[73],"of":[74,86,123],"human":[75],"evaluation.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,149],"summarize":[81],"most":[83],"important":[84],"aspects":[85],"their":[90],"evaluation,":[93],"providing":[94],"direct":[95],"links":[96],"NLP":[98,146],"tasks":[99],"NLP-specific":[101],"challenges":[102],"where":[103],"appropriate.":[104],"We":[105],"(i)":[106],"outline":[107],"general":[108],"study":[109],"design,":[110],"ethical":[111],"considerations,":[112],"factors":[114],"consider":[116],"crowdsourcing,":[118],"(ii)":[119],"discuss":[120],"particularities":[122],"provide":[129],"starting":[130],"points":[131],"select":[133],"questionnaires,":[134],"experimental":[135],"designs,":[136],"methods":[139],"are":[141],"tailored":[142],"specific":[145],"tasks.":[147],"Additionally,":[148],"offer":[150],"examples":[151],"with":[152],"accompanying":[153],"statistical":[154],"code,":[156],"bridge":[158],"gap":[160],"between":[161],"theoretical":[162],"guidelines":[163],"practical":[165],"applications.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}