{"id":"https://openalex.org/W4416035256","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1580","title":"HICode: Hierarchical Inductive Coding with LLMs","display_name":"HICode: Hierarchical Inductive Coding with LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035256","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1580"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1580","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1580","pdf_url":"https://aclanthology.org/2025.emnlp-main.1580.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1580.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119816305","display_name":"Mian Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mian Zhong","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048611471","display_name":"P. Wang","orcid":"https://orcid.org/0009-0003-3059-8795"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pristina Wang","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119816306","display_name":"Anjalie Field","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anjalie Field","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119816305"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34581021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31048","last_page":"31066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.06239999830722809,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.06239999830722809,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.03869999945163727,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03759999945759773,"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/coding","display_name":"Coding (social sciences)","score":0.5479000210762024},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5339999794960022},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4348999857902527},{"id":"https://openalex.org/keywords/qualitative-analysis","display_name":"Qualitative analysis","score":0.3718999922275543},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3352000117301941},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6539999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5806999802589417},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5339999794960022},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39809998869895935},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C2984309518","wikidata":"https://www.wikidata.org/wiki/Q181784","display_name":"Human trafficking","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C87156501","wikidata":"https://www.wikidata.org/wiki/Q7268708","display_name":"Qualitative property","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C59577422","wikidata":"https://www.wikidata.org/wiki/Q10265143","display_name":"False accusation","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1580","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1580","pdf_url":"https://aclanthology.org/2025.emnlp-main.1580.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1580","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1580","pdf_url":"https://aclanthology.org/2025.emnlp-main.1580.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035256.pdf","grobid_xml":"https://content.openalex.org/works/W4416035256.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"numerous":[1],"applications":[2],"for":[3,133],"fine-grained":[4],"corpus":[5],"analysis,":[6],"researchers":[7,41],"continue":[8],"to":[9,27,35,45,78,113],"rely":[10],"on":[11],"manual":[12],"labeling,":[13],"which":[14,24],"does":[15],"not":[16],"scale,":[17],"or":[18],"statistical":[19],"tools":[20],"like":[21],"topic":[22],"modeling,":[23],"are":[25],"difficult":[26],"control.We":[28],"propose":[29],"that":[30,40,64],"LLMs":[31],"have":[32],"the":[33,37,114,119],"potential":[34,132],"scale":[36],"nuanced":[38,135],"analyses":[39,136],"typically":[42],"conduct":[43,105],"manually":[44],"large":[46],"text":[47],"corpora.To":[48],"this":[49,83],"effect,":[50],"inspired":[51],"by":[52,89,126],"qualitative":[53],"research":[54],"methods,":[55],"we":[56,104],"develop":[57],"HICode":[58],"1":[59],",":[60],"a":[61,106],"two-part":[62],"pipeline":[63],"first":[65],"inductively":[66],"generates":[67],"labels":[68],"directly":[69],"from":[70],"analysis":[71],"data":[72],"and":[73,95,101,129],"then":[74],"hierarchically":[75],"clusters":[76],"them":[77],"surface":[79],"emergent":[80],"themes.We":[81],"validate":[82],"approach":[84],"across":[85],"three":[86],"diverse":[87],"datasets":[88],"measuring":[90],"alignment":[91],"with":[92],"human-constructed":[93],"themes":[94],"demonstrating":[96,130],"its":[97],"robustness":[98],"through":[99],"automated":[100],"human":[102],"evaluations.Finally,":[103],"case":[107],"study":[108],"of":[109],"litigation":[110],"documents":[111],"related":[112],"ongoing":[115],"opioid":[116],"crisis":[117],"in":[118,137],"U.S.,":[120],"revealing":[121],"aggressive":[122],"marketing":[123],"strategies":[124],"employed":[125],"pharmaceutical":[127],"companies":[128],"HICode's":[131],"facilitating":[134],"large-scale":[138],"data.":[139]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-11-08T00:00:00"}