{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001003035,0.001172462,0.0006959341,0.001844322,0.0003921358,0.0008662571,0.0008821939,0.0007469186,0.00325649],"category_scores_gemma":[0.003081109,0.0002957825,0.0007488275,0.000868991,0.0001640481,0.001746427,0.0007728979,0.0007826743,0.004290817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004360332,"about_ca_system_score_gemma":0.0005312797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001361497,"about_ca_topic_score_gemma":0.00361628,"domain_scores_codex":[0.9993412,0.0001113959,0.00006721298,0.0002342489,0.0001986477,0.00004742663],"domain_scores_gemma":[0.9986524,0.0003782007,0.0001697294,0.0001351053,0.0005957671,0.00006889415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001187181,0.0004946746,0.008253515,0.0007256062,0.0001771274,0.0007468467,0.0005652994,0.002939225,0.114973,0.00186278,0.09384286,0.7742318],"study_design_scores_gemma":[0.0003017945,0.0008423355,0.01634569,0.0001340056,0.0003044706,0.0008831701,0.0006990442,0.7493964,0.1474159,0.008759551,0.07475839,0.0001593886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1288663,0.001304986,0.7361767,0.001231368,0.000738347,0.001479587,0.01737221,0.0984905,0.0143401],"genre_scores_gemma":[0.2935782,0.0007709904,0.6448004,0.0007890315,0.0005093603,0.001051245,0.0426304,0.001120345,0.01475006],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00325649,"threshold_uncertainty_score":0.01089406,"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."}}