{"id":"W4402920036","doi":"10.1007/978-3-031-71918-9_3","title":"Towards AI-Assisted Protocol Analysis in Design Research: Automating Question Labelling with GPT-4 According to Eris’ (2004) Taxonomy","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Labelling; Taxonomy (biology); Computer science; Protocol (science); Information retrieval; Computational biology; Biology; Biochemistry; Medicine; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.02395786,0.001989707,0.001220958,0.004647026,0.002099636,0.01012358,0.003600206,0.003530818,0.01278381],"category_scores_gemma":[0.04996794,0.002064146,0.003331276,0.004291424,0.006371059,0.01171846,0.007394004,0.006253966,0.008377189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00305067,"about_ca_system_score_gemma":0.006060083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004725767,"about_ca_topic_score_gemma":0.006407284,"domain_scores_codex":[0.9712832,0.02034149,0.001996553,0.002549109,0.003268302,0.0005613911],"domain_scores_gemma":[0.9413163,0.0369007,0.002074657,0.01395317,0.005230058,0.0005251264],"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":[0.0001110771,0.0001673015,0.001509301,0.001611569,0.0001215998,0.0001872109,0.009871469,0.005069741,0.009844971,0.3997107,0.01913832,0.5526567],"study_design_scores_gemma":[0.00004668325,0.00006357623,0.0007411526,0.0008645414,0.0001355442,0.0005027099,0.001908079,0.08260775,0.02094205,0.7498094,0.1422805,0.00009807638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005798189,0.0001157028,0.9935748,0.0006157396,0.0000326159,0.0002399051,0.0001582871,0.001879268,0.002804002],"genre_scores_gemma":[0.01178882,0.0001546345,0.9841126,0.0002567736,0.00001748361,0.0003497536,0.0004963328,0.0005163786,0.002307161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02395786,"threshold_uncertainty_score":0.1267028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1198350428201419,"score_gpt":0.384692741145786,"score_spread":0.264857698325644,"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."}}