{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004607219,0.0004140588,0.0006366046,0.001293684,0.0003397086,0.00117103,0.001597909,0.000168589,0.000001731258],"category_scores_gemma":[0.0005969573,0.0003711593,0.0001069309,0.002034133,0.0002252933,0.002899888,0.0009520861,0.001168149,0.000002868011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003642578,"about_ca_system_score_gemma":0.000440922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002944345,"about_ca_topic_score_gemma":0.000008170727,"domain_scores_codex":[0.9956949,0.000209416,0.0007042858,0.001137031,0.001283594,0.0009707093],"domain_scores_gemma":[0.9959334,0.0009968608,0.0002250321,0.0003415513,0.002341252,0.0001619411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002644038,0.0002192566,0.00001111046,0.000874958,0.0001291534,0.00001714932,0.4881935,0.000007404244,0.02781954,0.4784906,0.0003388803,0.003871958],"study_design_scores_gemma":[0.0004215852,0.001051154,0.000004907116,0.00191272,0.00002157898,0.00001346473,0.1231867,0.4492082,0.1260377,0.2975498,0.00005831954,0.0005338329],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1395938,0.0004779467,0.8529095,0.001752457,0.0001092797,0.002718674,0.00001275012,0.002144573,0.0002809849],"genre_scores_gemma":[0.8072058,0.00001584966,0.1916766,0.00001175733,0.0000936845,0.000879904,0.000005004136,0.00004145936,0.00006992432],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.667612,"threshold_uncertainty_score":0.9998741,"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."}}