{"id":"W2963838871","doi":"10.1145/3325281","title":"Concurrent Think-Aloud Verbalizations and Usability Problems","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Computer-Human Interaction","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Usability; Think aloud protocol; Computer science; Protocol analysis; Human–computer interaction; Protocol (science); Visualization; Focus (optics); Modality (human–computer interaction); Psychology; Artificial intelligence; Cognitive science","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":[0.03965173,0.001649657,0.0008008631,0.002087773,0.001395992,0.003746832,0.00152478,0.001430452,0.002121068],"category_scores_gemma":[0.307001,0.001026186,0.000609091,0.001363242,0.003205997,0.00358602,0.002913711,0.002588845,0.0004674788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001814008,"about_ca_system_score_gemma":0.001889631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001258249,"about_ca_topic_score_gemma":0.00108426,"domain_scores_codex":[0.9159605,0.04878877,0.008456558,0.005025879,0.02044781,0.001320541],"domain_scores_gemma":[0.5503022,0.3286411,0.0560381,0.02045105,0.04281909,0.001748425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.006112467,0.00210311,0.116657,0.004208538,0.0006320822,0.001545958,0.5374719,0.003884773,0.08549555,0.0136284,0.004774163,0.223486],"study_design_scores_gemma":[0.001414757,0.01001739,0.3854185,0.003945072,0.0008943639,0.0064305,0.274815,0.05296549,0.1389063,0.08493976,0.03848258,0.001770233],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8961,0.000709596,0.09092217,0.0009467765,0.0002154942,0.001943626,0.0002404974,0.0008720738,0.008049761],"genre_scores_gemma":[0.9726752,0.0002228527,0.02190375,0.0003255744,0.00004870916,0.002697891,0.0002219968,0.0002224117,0.001681681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03965173,"threshold_uncertainty_score":0.2097009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03467616129877977,"score_gpt":0.2867475151867631,"score_spread":0.2520713538879834,"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."}}