{"id":"https://openalex.org/W7140101711","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.351","title":"Training-Free Text Emotion Tagging via LLM-Based Best-Worst Scaling","display_name":"Training-Free Text Emotion Tagging via LLM-Based Best-Worst Scaling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140101711","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.351"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.351","pdf_url":"https://aclanthology.org/2026.findings-eacl.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.351.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130339515","display_name":"Lukas Christ","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Christ","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010754413","display_name":"Shahin Amiriparian","orcid":"https://orcid.org/0000-0002-1129-8223"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shahin Amiriparian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24765933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6678","last_page":"6694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7692999839782715,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7692999839782715,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04600000008940697,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.033799998462200165,"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/scaling","display_name":"Scaling","score":0.4131999909877777},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.32739999890327454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29809999465942383},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.2824000120162964},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2736999988555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.621399998664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309000015258789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.351","pdf_url":"https://aclanthology.org/2026.findings-eacl.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.351","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.351","pdf_url":"https://aclanthology.org/2026.findings-eacl.351.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140101711.pdf","grobid_xml":"https://content.openalex.org/works/W7140101711.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"been":[5],"frequently":[6],"used":[7],"as":[8,14,106,108],"automatic":[9,141],"annotators":[10,24],"for":[11,67,96,148],"tasks":[12],"such":[13],"Text":[15],"Emotion":[16],"Recognition":[17],"(TER).We":[18],"consider":[19],"a":[20,32,38,47,68,81],"scenario":[21],"in":[22,127],"which":[23],"assign":[25],"at":[26],"least":[27,62],"one":[28],"emotion":[29,42,151],"label":[30,73],"from":[31,71],"large":[33],"set":[34],"of":[35,117,129],"options":[36],"to":[37,59,121,124,136,145],"text":[39,70],"snippet.For":[40],"this":[41,90],"tagging":[43],"task,":[44],"we":[45],"propose":[46],"novel":[48],"zero-shot":[49],"algorithm":[50,101],"that":[51],"leverages":[52],"Best-Worst":[53],"Scaling":[54],"(BWS),":[55],"prompting":[56,104],"the":[57,61,93,115,118,125,162],"LLM":[58],"choose":[60],"and":[63,132],"most":[64],"suitable":[65,147],"emotions":[66],"given":[69],"several":[72],"subsets.The":[74],"LLM's":[75],"choices":[76],"can":[77],"be":[78,146],"represented":[79],"by":[80],"graph":[82,91],"linking":[83],"labels":[84],"via":[85],"worse-than":[86],"relations.Random":[87],"walks":[88],"on":[89],"yield":[92],"final":[94],"score":[95],"each":[97],"label.We":[98],"compare":[99,122],"our":[100,139],"with":[102,134],"naive":[103],"approaches":[105],"well":[107],"an":[109],"established":[110,163],"BWSbased":[111],"method.Extensive":[112],"experiments":[113],"demonstrate":[114],"suitability":[116],"method.It":[119],"proves":[120],"favorably":[123],"benchmarks":[126],"terms":[128],"both":[130],"accuracy":[131],"calibration":[133],"respect":[135],"human":[137],"annotations.Moreover,":[138],"algorithm's":[140],"annotations":[142],"are":[143],"shown":[144],"finetuning":[149],"lightweight":[150],"classification":[152],"models.The":[153],"proposed":[154],"method":[155],"consumes":[156],"considerably":[157],"fewer":[158],"computational":[159],"resources":[160],"than":[161],"BWS":[164],"approach.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}