{"id":"W1990800148","doi":"10.22318/cscl2009.2.162","title":"Automating the analysis of collaborative discourse: identifying idea clusters","year":2009,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Complement (music); Latent semantic analysis; Visualization; Qualitative analysis; Data visualization; Quantitative analysis (chemistry); Data science; Semantic analysis (machine learning); Discourse analysis; Scale (ratio); Information retrieval; Natural language processing; Qualitative research; Data mining; Linguistics; Sociology","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004252479,0.00024271,0.0006400593,0.0008644236,0.0008443219,0.00003694777,0.000829172,0.0002181307,0.0009702414],"category_scores_gemma":[0.0003574791,0.0002315356,0.0003801757,0.003925982,0.0004605629,0.0003972464,0.000147696,0.0008406432,0.00004277849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001194721,"about_ca_system_score_gemma":0.00007067357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001851228,"about_ca_topic_score_gemma":0.0001070649,"domain_scores_codex":[0.9958672,0.002340331,0.0003875656,0.0004751955,0.0005151468,0.0004145617],"domain_scores_gemma":[0.9973865,0.0005844211,0.0008608061,0.0007177411,0.0003629824,0.00008756332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001150217,0.000619564,0.6339743,0.00007544177,0.007379412,0.00009383407,0.2279638,0.002121575,0.04661362,0.01696991,0.001101034,0.06193725],"study_design_scores_gemma":[0.0007843545,0.0001310388,0.9697757,0.00006746376,0.001093111,0.000003956909,0.02659888,0.0002659677,0.0004343587,0.0002578965,0.0003528579,0.0002343796],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827188,0.0001965459,0.005085472,0.001312533,0.0002314909,0.0002211622,0.00004410762,0.00008661723,0.01010325],"genre_scores_gemma":[0.9917255,0.000003547462,0.004579826,0.0001611371,0.00004032098,4.048997e-7,0.00003702176,0.00001598642,0.003436232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3358014,"threshold_uncertainty_score":0.999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04006043594522722,"score_gpt":0.3595504102161274,"score_spread":0.3194899742709001,"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."}}