{"id":"W4205689905","doi":"10.1109/smc52423.2021.9658689","title":"ONSET: Opinion and Aspect Extraction System from Unlabelled Data","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Sentiment analysis; Artificial intelligence; Language model; Natural language processing; Quality (philosophy); Machine learning; State (computer science); Information extraction; Training set; Data modeling; Database","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003777316,0.0002233912,0.0003262906,0.0001469425,0.0001450128,0.001122345,0.0007369469,0.000107564,0.0001422046],"category_scores_gemma":[0.00003882355,0.000218054,0.00004677717,0.0001691002,0.00004234133,0.0004203203,0.0003697576,0.0001779928,0.00009683429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006663462,"about_ca_system_score_gemma":0.00009613896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004122998,"about_ca_topic_score_gemma":0.00007563546,"domain_scores_codex":[0.9975998,0.0001938616,0.0004960677,0.0008901551,0.000624697,0.0001954533],"domain_scores_gemma":[0.9983072,0.0001923294,0.0002762112,0.0007769321,0.0003267669,0.0001205608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001068178,0.0004988172,0.01157418,0.0002451597,0.001639536,0.0003882383,0.001793765,0.0003449988,0.01086638,0.9081775,0.01660767,0.04775697],"study_design_scores_gemma":[0.0012717,0.0001067425,0.005444726,0.001097959,0.00008150507,0.0001764979,0.002876376,0.9449214,0.002169619,0.000674314,0.04054832,0.000630836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4068883,0.01189397,0.442704,0.007699995,0.03477441,0.001219757,0.001035727,0.000495061,0.0932888],"genre_scores_gemma":[0.9928717,0.001596014,0.001832899,0.00009457704,0.0005442096,0.00001149392,0.0003872835,0.00001353286,0.00264829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445764,"threshold_uncertainty_score":0.9999146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1045278426116045,"score_gpt":0.3315195991100384,"score_spread":0.2269917564984339,"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."}}