{"id":"W4383106218","doi":"10.1007/s10489-023-04677-3","title":"Developing a closed captioning quality assessment system using a multi-label classifier with active learning from deaf and hard of hearing viewers","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Subtitles and Audiovisual Media","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Closed captioning; Computer science; Classifier (UML); CLIPS; Quality assessment; Perception; Machine learning; Artificial intelligence; Replicate; Quality (philosophy); Multimedia; Human–computer interaction; Evaluation methods","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003008333,0.0001563398,0.0002956461,0.00009029917,0.000317525,0.0000981002,0.00009123389,0.00004441675,0.00005398822],"category_scores_gemma":[0.00002771636,0.0001325253,0.00002775645,0.0001103168,0.0001648321,0.0001051221,0.00007890601,0.0002103097,0.00002341436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001251019,"about_ca_system_score_gemma":0.00008238088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001369315,"about_ca_topic_score_gemma":0.0003227078,"domain_scores_codex":[0.9988655,0.00005349087,0.0003211284,0.0003013165,0.0002277101,0.000230781],"domain_scores_gemma":[0.9992824,0.0002432016,0.0002086355,0.000116042,0.00009774257,0.00005203278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002583734,0.0001160387,0.007239459,0.001027066,0.0006013046,0.0000244433,0.1391608,0.002151468,0.04863934,0.5885248,0.00001408963,0.2122428],"study_design_scores_gemma":[0.001637485,0.0002563141,0.03118555,0.003589519,0.0002531268,0.000007508463,0.7045525,0.2061973,0.04681847,0.001506509,0.002386667,0.001609055],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9450473,0.00005583857,0.05235421,0.00001912107,0.000157918,0.0002371002,0.000008879078,0.000115401,0.002004265],"genre_scores_gemma":[0.9874868,0.00003276395,0.01218088,0.00002810209,0.00009491594,0.00003105054,0.00001428903,0.00002389964,0.0001073506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5870183,"threshold_uncertainty_score":0.5404226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3310200961169075,"score_gpt":0.3667871010453493,"score_spread":0.03576700492844181,"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."}}