{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04519558,0.002326309,0.0009271849,0.00234313,0.0009729911,0.002079825,0.002412651,0.00165509,0.002720846],"category_scores_gemma":[0.08591352,0.00140758,0.0009074935,0.00102031,0.001271715,0.002265331,0.002549866,0.001529084,0.001172716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001363455,"about_ca_system_score_gemma":0.00336839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001350294,"about_ca_topic_score_gemma":0.001965512,"domain_scores_codex":[0.9581826,0.03183457,0.003725106,0.002085613,0.003248829,0.0009232048],"domain_scores_gemma":[0.9042973,0.06699398,0.003378306,0.006985608,0.01572984,0.00261506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002815663,0.01141959,0.02104095,0.0045314,0.0001996525,0.0008412686,0.03996164,0.008633338,0.06691545,0.0038661,0.005641327,0.8341335],"study_design_scores_gemma":[0.01135083,0.07405451,0.1298286,0.006909681,0.00159569,0.003635592,0.03644457,0.2535315,0.2829283,0.01824944,0.1789518,0.002519382],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3184555,0.0004701247,0.6141816,0.0004070204,0.000210114,0.0550581,0.0005145851,0.006810783,0.003892311],"genre_scores_gemma":[0.1959428,0.0001756325,0.7684573,0.0001149819,0.00003075859,0.03353041,0.0002617187,0.0002941735,0.001192296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04519558,"threshold_uncertainty_score":0.2390199,"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."}}