{"id":"W4380238498","doi":"10.1177/00472395231178943","title":"Conversation-Based Assessments in Education: Design, Implementation, and Cognitive Walkthroughs for Usability Testing","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Technology Systems","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Concordia University of Edmonton","funders":"","keywords":"Usability; Conversation; Formative assessment; Cognitive walkthrough; Software walkthrough; Computer science; Usability lab; Usability engineering; Pluralistic walkthrough; Cognition; Human–computer interaction; Psychology; Mathematics education; Software; Software system","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":[],"consensus_categories":[],"category_scores_codex":[0.001376473,0.00009797357,0.000194909,0.0006711661,0.0001225468,0.00008753798,0.0002540618,0.00007590769,0.00000443448],"category_scores_gemma":[0.0008099089,0.000094403,0.00003134583,0.0009149663,0.0000477764,0.0003408802,0.00003048496,0.0001451946,0.000005828735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001925089,"about_ca_system_score_gemma":0.001438172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005605675,"about_ca_topic_score_gemma":0.000003540653,"domain_scores_codex":[0.9987049,0.0001200286,0.0005981047,0.0002034728,0.0001987473,0.0001747801],"domain_scores_gemma":[0.9964131,0.001806602,0.0005675776,0.0001128541,0.001058553,0.000041333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001994957,0.000244287,0.6815758,0.0002051058,0.00009215623,0.000002958907,0.001067037,0.002701443,0.0006785452,0.2914706,0.001208634,0.02073346],"study_design_scores_gemma":[0.006434042,0.00318868,0.5730827,0.00456475,0.0001488988,0.0006863599,0.1341955,0.1383629,0.004946901,0.1183363,0.01458627,0.001466638],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3304832,0.0007269319,0.6517237,0.01244604,0.003307588,0.001161497,0.00000645995,0.00007058463,0.00007398196],"genre_scores_gemma":[0.9757894,0.000003315263,0.02363518,0.00004434993,0.0001771268,0.0001509033,0.000005136359,0.000006943006,0.0001877009],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6453061,"threshold_uncertainty_score":0.3849642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07061014901884904,"score_gpt":0.3948647745414356,"score_spread":0.3242546255225866,"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."}}