{"id":"W4312307609","doi":"10.1109/access.2022.3227504","title":"Characterizing UX Evaluation in Software Modeling Tools: A Literature Review","year":2022,"lang":"en","type":"review","venue":"IEEE Access","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Usability; Software engineering; Software; User experience design; Data science; Heuristics; Human–computer interaction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01466352,0.001336184,0.003196981,0.01860822,0.001148752,0.004494004,0.001570212,0.001930858,0.002539862],"category_scores_gemma":[0.04884411,0.001093425,0.002275966,0.01936924,0.001281703,0.005138339,0.001852465,0.001416383,0.0006519187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003371629,"about_ca_system_score_gemma":0.01003524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005235215,"about_ca_topic_score_gemma":0.007920207,"domain_scores_codex":[0.99013,0.003823268,0.002342687,0.0006720757,0.002784486,0.0002474823],"domain_scores_gemma":[0.9201321,0.06332456,0.004444874,0.0009533596,0.01066219,0.0004828974],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00008724759,0.0001073304,0.001274981,0.2141135,0.0004674824,0.0001729515,0.001711276,0.00040982,0.0006301221,0.003658863,0.006270861,0.7710957],"study_design_scores_gemma":[0.00005319098,0.0005227856,0.01149484,0.5844808,0.004538405,0.0013206,0.00453519,0.0007850528,0.001868478,0.004303864,0.3859601,0.0001366065],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00115435,0.9957466,0.0009243702,0.000554738,0.0001322293,0.0000987547,0.00004789605,0.00001387536,0.00132729],"genre_scores_gemma":[0.008201044,0.989109,0.001814479,0.0002716515,0.00009857715,0.0001792196,0.00008588758,0.00001131985,0.0002287594],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9853365,"threshold_uncertainty_score":0.07754904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2212494196626109,"score_gpt":0.4263504079794989,"score_spread":0.2051009883168881,"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."}}