{"id":"W3152918650","doi":"10.1007/s10664-023-10314-x","title":"Evaluating pre-trained models for user feedback analysis in software engineering: a study on classification of app-reviews","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Artificial intelligence; F1 score; Macro; Set (abstract data type); Task (project management); Binary classification; Support vector machine; Data mining; Engineering","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002576156,0.0004885182,0.0009567635,0.00184133,0.00007305111,0.0001173518,0.001291969,0.0001962051,0.000007067131],"category_scores_gemma":[0.01290504,0.0004883591,0.0004038564,0.007436054,0.00001887842,0.0004597587,0.0003384952,0.0004916502,0.00002817297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000323961,"about_ca_system_score_gemma":0.00009707417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001813176,"about_ca_topic_score_gemma":0.000005851226,"domain_scores_codex":[0.9958406,0.0001140525,0.001078433,0.001054386,0.001003163,0.0009093457],"domain_scores_gemma":[0.9932325,0.004889186,0.0001661081,0.001257332,0.0002130137,0.0002418632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001880388,0.0002074413,0.1099487,0.0002343747,0.0001823667,0.000007519881,0.001347109,0.8845833,0.0003143036,0.00008745297,0.0002206327,0.002847994],"study_design_scores_gemma":[0.0005524695,0.0002467075,0.4095843,0.00009286507,0.00004906128,7.547147e-7,0.00001728067,0.5888278,0.00008517168,0.00003224758,0.0002042895,0.0003070512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3983337,0.0001055312,0.5989581,0.0000570318,0.000169113,0.001187512,0.00001102716,0.001177166,7.620014e-7],"genre_scores_gemma":[0.8580238,0.00001217833,0.1404041,0.00002258763,0.00009277896,0.001213357,0.00004239042,0.00009448398,0.00009441034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.45969,"threshold_uncertainty_score":0.9997568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1510793216345061,"score_gpt":0.4013715572634857,"score_spread":0.2502922356289796,"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."}}