{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01592098,0.001905792,0.001533213,0.004577098,0.001201198,0.001705419,0.001505227,0.00157105,0.0007482875],"category_scores_gemma":[0.02032055,0.0003297407,0.001771274,0.003305621,0.0007376197,0.002886417,0.001713478,0.001674463,0.0009227493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009285034,"about_ca_system_score_gemma":0.0008247634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002943391,"about_ca_topic_score_gemma":0.005065266,"domain_scores_codex":[0.99256,0.002687245,0.001059325,0.001696095,0.001593686,0.0004036101],"domain_scores_gemma":[0.9788519,0.01131377,0.001301146,0.002693726,0.005065113,0.000774361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003514542,0.003937093,0.4338804,0.002828625,0.004152777,0.0005851057,0.001248386,0.03728474,0.02514066,0.001221966,0.06610791,0.4200977],"study_design_scores_gemma":[0.0007220311,0.004570428,0.3693216,0.0005284521,0.001922825,0.002273798,0.002911543,0.5461591,0.03649783,0.002833791,0.0319651,0.0002935514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.943196,0.004534011,0.02155828,0.0007559565,0.0005173709,0.0009092282,0.022641,0.002352532,0.003535759],"genre_scores_gemma":[0.7963675,0.001006771,0.08142878,0.000397955,0.0003311815,0.0008456191,0.1177944,0.0002096488,0.001618089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01592098,"threshold_uncertainty_score":0.08419919,"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."}}