{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00251057,0.0004299925,0.001145244,0.0004304007,0.00009878509,0.001115702,0.003160859,0.0002156526,0.00008162641],"category_scores_gemma":[0.001048447,0.0003899431,0.0003022179,0.001992084,0.000005200426,0.00344972,0.0006682234,0.001138996,0.00001062145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003079366,"about_ca_system_score_gemma":0.0003421428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001343738,"about_ca_topic_score_gemma":0.000001521163,"domain_scores_codex":[0.9969409,0.0005344667,0.000769338,0.0007629336,0.0006632604,0.0003291098],"domain_scores_gemma":[0.9975786,0.0006299082,0.0004773295,0.001136689,0.0001150016,0.00006247858],"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":[4.011463e-7,0.00001485719,3.555871e-7,0.02639584,0.00001618093,0.00004483861,0.00005008479,0.0001453424,3.078332e-8,0.00002363674,0.0003061472,0.9730023],"study_design_scores_gemma":[0.0000441753,0.00001401069,3.264308e-7,0.09711111,0.0001425775,0.0001003572,3.190792e-7,0.01177556,3.04887e-7,0.000133646,0.8902488,0.0004288647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.88695e-7,0.7855968,0.2117901,0.00004849029,0.0009402868,0.001108125,0.00001512558,0.0004540909,0.00004668821],"genre_scores_gemma":[0.000001199155,0.9820991,0.01553672,0.0004279589,0.0001650597,0.001541628,0.0001681001,0.00004827717,0.00001192477],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9725734,"threshold_uncertainty_score":0.9999213,"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."}}