{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003158608,0.0002821106,0.0002776227,0.0002137978,0.0003929811,0.0004264694,0.0008545993,0.0001235908,0.0002911026],"category_scores_gemma":[0.00001633668,0.0002835133,0.0001414773,0.0003306827,0.00008445316,0.001407829,0.00006320333,0.000500428,0.0002733897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001995493,"about_ca_system_score_gemma":0.0000395977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087487,"about_ca_topic_score_gemma":0.00007877233,"domain_scores_codex":[0.9978586,0.00022253,0.0004850378,0.0008252612,0.0003084096,0.0003000957],"domain_scores_gemma":[0.9978761,0.0003927429,0.0001429592,0.001279206,0.0001741953,0.0001347903],"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":[0.0001155133,0.00619438,0.003597663,0.0008983287,0.0006748285,0.00001256857,0.04245052,0.1070685,0.009609146,0.04765968,0.003281249,0.7784377],"study_design_scores_gemma":[0.003352389,0.004331131,0.01369467,0.0007426883,0.0001108644,0.0002173234,0.0006742632,0.9210237,0.01223235,0.02358469,0.0182002,0.001835783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2615527,0.00001624907,0.7344692,0.0006587497,0.002284265,0.0004807962,0.000007540943,0.0003216682,0.0002088694],"genre_scores_gemma":[0.990639,0.00001525299,0.008657487,0.0002902829,0.00006969059,0.00002177168,0.00001006114,0.00001738922,0.0002790662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8139552,"threshold_uncertainty_score":0.9999617,"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."}}