{"id":"W3211925781","doi":"10.1145/3491211","title":"An Empirical Study of the Effectiveness of an Ensemble of Stand-alone Sentiment Detection Tools for Software Engineering Datasets","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; University of Saskatchewan; Concordia University; University of Calgary","funders":"","keywords":"Computer science; Sentiment analysis; Software; Majority rule; Artificial intelligence; Machine learning; Empirical research; Detector; Data mining","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":[0.00287029,0.0002099154,0.0004801163,0.0003685628,0.0001547694,0.00002010606,0.0008719307,0.00008627072,0.000003538603],"category_scores_gemma":[0.003296879,0.0001990257,0.0001030329,0.000680285,0.00003500121,0.0002818709,0.0001019745,0.0003819431,7.496275e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008922373,"about_ca_system_score_gemma":0.00006776649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005360524,"about_ca_topic_score_gemma":0.000004859884,"domain_scores_codex":[0.9976015,0.0008576874,0.0003924439,0.0004697349,0.0003845737,0.0002940759],"domain_scores_gemma":[0.9866105,0.01188666,0.00009849531,0.001196851,0.0001111859,0.00009632719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002894886,0.0007602077,0.001668442,0.0005159131,0.0001874046,0.000003611494,0.001164887,0.916549,0.04598032,0.00002698751,0.000001469324,0.03285226],"study_design_scores_gemma":[0.004729222,0.01093759,0.1655333,0.0001794009,0.0002537319,0.000168298,0.0006876738,0.1001418,0.7160993,0.0002141216,0.0002680758,0.000787482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4619716,0.00004839179,0.5370426,0.000003161372,0.0003095055,0.0004171982,0.00009985208,0.0001077167,2.460512e-8],"genre_scores_gemma":[0.7073179,0.000002823304,0.2924002,0.000002847474,0.000009893187,0.0002299674,0.000009497179,0.00002545705,0.000001347035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8164071,"threshold_uncertainty_score":0.8116032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0814680668414065,"score_gpt":0.3610115127954521,"score_spread":0.2795434459540456,"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."}}