{"id":"W4402761492","doi":"10.3390/systems12090380","title":"Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering","year":2024,"lang":"en","type":"article","venue":"Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Social Science Fund of China; Fundo para o Desenvolvimento das Ciências e da Tecnologia; China Scholarship Council; Science and Technology Development Fund","keywords":"Cluster analysis; Coding (social sciences); Computer science; Psychology; Natural language processing; Artificial intelligence; Mathematics; Statistics","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":[0.01105763,0.003012038,0.001472339,0.005643639,0.00130704,0.002130603,0.00417071,0.001704287,0.01353827],"category_scores_gemma":[0.03896495,0.0009647623,0.001324653,0.002690676,0.001107839,0.003689086,0.005571673,0.002533039,0.01218271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037336,"about_ca_system_score_gemma":0.002696894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004699548,"about_ca_topic_score_gemma":0.005887085,"domain_scores_codex":[0.9892778,0.003842574,0.00129967,0.002594492,0.00259696,0.0003884509],"domain_scores_gemma":[0.9762549,0.007172976,0.001730037,0.004226464,0.009678971,0.0009365978],"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":[0.0006959721,0.0004669591,0.003516662,0.0003774054,0.00009866733,0.0001765025,0.001865972,0.007930658,0.01448568,0.004969094,0.04493357,0.9204829],"study_design_scores_gemma":[0.0003539816,0.0005551111,0.006624476,0.0002062182,0.00009484368,0.0003904067,0.001161274,0.8466845,0.05152947,0.02988021,0.06213217,0.000387295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006080092,0.00005289437,0.9353386,0.0001658718,0.00007893092,0.001400138,0.001325096,0.05414874,0.001409696],"genre_scores_gemma":[0.04090064,0.00004624528,0.9488999,0.0001303476,0.00004024018,0.002237915,0.003085834,0.001635909,0.003023006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01353827,"threshold_uncertainty_score":0.05847901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01578249369765576,"score_gpt":0.2975465830359427,"score_spread":0.2817640893382869,"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."}}