{"id":"W1991867644","doi":"10.1007/s10664-015-9375-7","title":"Analyzing and automatically labelling the types of user issues that are raised in mobile app reviews","year":2015,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"App store; Computer science; World Wide Web; Download; Internet privacy; Mobile apps; Mobile device; Analytics; Notice; Data science","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":[0.001170562,0.0001997656,0.0004114475,0.0001856222,0.00003515461,0.00009705221,0.0006658933,0.00008780358,0.000006310668],"category_scores_gemma":[0.003888967,0.0001468129,0.00006150576,0.0008552639,0.00004147855,0.0002726501,0.0003394883,0.0003326852,0.00001628811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007326922,"about_ca_system_score_gemma":0.00004101483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001358957,"about_ca_topic_score_gemma":0.000002331447,"domain_scores_codex":[0.9984935,0.00006663286,0.000363211,0.0003258917,0.0003718229,0.0003789444],"domain_scores_gemma":[0.9976998,0.001462949,0.00007170482,0.000513136,0.00007704385,0.0001753777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008667386,0.00008764648,0.8681135,0.0005288202,0.00005258004,0.0000481574,0.003370517,0.1150562,0.0001667048,0.0002308908,0.002288599,0.01004777],"study_design_scores_gemma":[0.001367344,0.0002518017,0.5650966,0.001523841,0.0000295573,0.0000458683,0.0001299552,0.3343301,0.001941337,0.000435739,0.09367935,0.001168482],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3242166,0.01530905,0.6590646,0.0003372069,0.0001803387,0.0003807817,0.000001286312,0.000503575,0.000006593834],"genre_scores_gemma":[0.8334458,0.0004142507,0.1657062,0.00007416616,0.0001037615,0.0001228668,0.000001657666,0.0000463116,0.00008497946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5092292,"threshold_uncertainty_score":0.5986856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05224016304009076,"score_gpt":0.3190022140689671,"score_spread":0.2667620510288763,"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."}}