{"id":"https://openalex.org/W4414969263","doi":"https://doi.org/10.18653/v1/2026.acl-long.92","title":"What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification","display_name":"What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414969263","doi":"https://doi.org/10.18653/v1/2026.acl-long.92"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.92","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.92","pdf_url":"https://aclanthology.org/2026.acl-long.92.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.92.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060472601","display_name":"Andrew Halterman","orcid":"https://orcid.org/0000-0001-9716-9555"},"institutions":[{"id":"https://openalex.org/I22675022","display_name":"Williams College","ror":"https://ror.org/04avkmd49","country_code":"US","type":"education","lineage":["https://openalex.org/I22675022"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Halterman","raw_affiliation_strings":["Michigan State University Williams College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University Williams College","institution_ids":["https://openalex.org/I22675022"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062069583","display_name":"Katherine A. Keith","orcid":null},"institutions":[{"id":"https://openalex.org/I22675022","display_name":"Williams College","ror":"https://ror.org/04avkmd49","country_code":"US","type":"education","lineage":["https://openalex.org/I22675022"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine A. Keith","raw_affiliation_strings":["Michigan State University Williams College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University Williams College","institution_ids":["https://openalex.org/I22675022"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22675022"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0103787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2043","last_page":"2059"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0731000006198883,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0731000006198883,"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/conceptualization","display_name":"Conceptualization","score":0.9855999946594238},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6474999785423279},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6402999758720398},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5576000213623047},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4821000099182129}],"concepts":[{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.9855999946594238},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5184000134468079},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4684000015258789},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2924000024795532},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.92","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.92","pdf_url":"https://aclanthology.org/2026.acl-long.92.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.03541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03541","pdf_url":"https://arxiv.org/pdf/2510.03541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.03541","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.03541","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.92","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.92","pdf_url":"https://aclanthology.org/2026.acl-long.92.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414969263.pdf","grobid_xml":"https://content.openalex.org/works/W4414969263.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5],"now":[6],"used":[7],"extensively":[8],"for":[9,145],"text":[10],"classification":[11],"in":[12,39,49,138],"computational":[13],"social":[14],"science":[15],"(CSS).In":[16],"this":[17,157],"work,":[18],"we":[19,102],"focus":[20],"on":[21,156],"the":[22,31,139],"steps":[23,45],"before":[24],"and":[25,35,54,97,141],"after":[26],"LLM":[27,37,88,120],"prompting:":[28],"conceptualization":[29,61,105,132],"of":[30,51],"categories":[32],"to":[33,59,75,95],"classify":[34,96],"using":[36],"predictions":[38],"downstream":[40,108,150],"statistical":[41],"inference.We":[42],"argue":[43],"these":[44],"have":[46],"been":[47],"overlooked":[48],"much":[50],"LLM-era":[52,140],"CSS":[53,129],"LLMs":[55,70],"can":[56,89],"tempt":[57],"analysts":[58,130],"skip":[60],"altogether.For":[62],"example,":[63],"a":[64,77,117,135],"political":[65],"scientist":[66],"classifying":[67],"\"protest\"":[68],"with":[69],"may":[71],"never":[72],"be":[73,113],"forced":[74],"craft":[76],"definition:":[78],"unlike":[79],"human":[80],"annotators":[81],"who":[82],"would":[83],"ask":[84],"clarifying":[85],"questions,":[86],"an":[87,92],"silently":[90],"accept":[91],"underspecified":[93],"concept":[94],"return":[98],"plausible-looking":[99],"labels.Using":[100],"simulations,":[101],"show":[103],"that":[104,111,131],"failures":[106],"induce":[107],"inferential":[109],"bias":[110,123],"cannot":[112],"corrected":[114],"solely":[115],"by":[116,127],"more":[118],"accurate":[119],"or":[121],"posthoc":[122],"correction":[124],"methods.We":[125],"conclude":[126],"reminding":[128],"is":[133],"still":[134],"first-order":[136],"concern":[137],"provide":[142],"concrete":[143],"advice":[144],"pursuing":[146],"low-cost,":[147],"unbiased,":[148],"low-variance":[149],"estimates.4":[151],"\u00a7A":[152],"provides":[153],"greater":[154],"details":[155],"terminology.":[158]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-09T00:00:00"}