{"id":"W4402423727","doi":"10.24908/iqurcp18054","title":"Leveraging Large Language Models for Automating Inductive Qualitative Coding: A Comparative Study of Prompt Engineering Techniques","year":2024,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Coding (social sciences); Inductive reasoning; Programming language; Inductive method; Software engineering; Natural language processing; Artificial intelligence; Mathematics education; Teaching method; Psychology; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0878983,0.001278674,0.0007756607,0.003024497,0.001366319,0.003992727,0.003244111,0.001259913,0.003021029],"category_scores_gemma":[0.2871814,0.0009113225,0.00108223,0.002149492,0.003456484,0.008199112,0.006763025,0.002562233,0.001197411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00371907,"about_ca_system_score_gemma":0.005510842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001799038,"about_ca_topic_score_gemma":0.003626449,"domain_scores_codex":[0.8881613,0.09864073,0.003007149,0.004016886,0.005350132,0.0008237702],"domain_scores_gemma":[0.4666989,0.4817317,0.008063257,0.02740995,0.01498815,0.001108036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008620865,0.0006046005,0.008941511,0.003955853,0.0001296952,0.0004263759,0.1746078,0.01432042,0.01713576,0.02985584,0.002528147,0.7466319],"study_design_scores_gemma":[0.0008746142,0.003113602,0.0142145,0.004956551,0.0004952736,0.003159182,0.150299,0.4195047,0.08451139,0.1955944,0.1224755,0.0008012949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07478977,0.0003534402,0.9170451,0.0007740102,0.00005625899,0.001786437,0.0002607163,0.001711118,0.003223225],"genre_scores_gemma":[0.2080025,0.0003411327,0.7877709,0.0002671484,0.00002149259,0.002177549,0.0003138047,0.0003764098,0.0007290196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0878983,"threshold_uncertainty_score":0.4648562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1761555671415186,"score_gpt":0.4539327931313133,"score_spread":0.2777772259897947,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}