{"id":"W2738173662","doi":"","title":"Semi-supervised learning and opinion-oriented information extraction","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Co-training; Classifier (UML); Graph; Semi-supervised learning; Naive Bayes classifier; Bottleneck; Information extraction; Supervised learning; Decision tree; Algorithm; Data mining; Theoretical computer science; Support vector machine","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":[0.006709149,0.001085206,0.001502417,0.003746492,0.0007282461,0.002039872,0.002239137,0.001370234,0.001661479],"category_scores_gemma":[0.02224754,0.0005977055,0.001579765,0.002564058,0.001687396,0.003536651,0.001681882,0.001800901,0.001078446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001158577,"about_ca_system_score_gemma":0.0009996759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009629146,"about_ca_topic_score_gemma":0.001214153,"domain_scores_codex":[0.9933334,0.003043674,0.0006258982,0.001391822,0.001414852,0.0001903703],"domain_scores_gemma":[0.9765759,0.01560592,0.002246645,0.001899332,0.003457492,0.0002147542],"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":[0.0002598178,0.0003782704,0.004992396,0.001122463,0.0005016461,0.0003296018,0.001064264,0.2245454,0.008910583,0.08378337,0.01144237,0.6626699],"study_design_scores_gemma":[0.00001680474,0.00004003746,0.0006357171,0.00004836892,0.00003019924,0.00007313819,0.00006340053,0.9318822,0.003338603,0.06158572,0.002262037,0.00002382275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007720132,0.0002688356,0.9899158,0.0002527115,0.00003646784,0.00008867015,0.0001400022,0.0004464336,0.001131002],"genre_scores_gemma":[0.3250152,0.0005988371,0.6692625,0.0003630901,0.0002939723,0.0004860842,0.001550297,0.0001734755,0.002256615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006709149,"threshold_uncertainty_score":0.03548175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008705654857859608,"score_gpt":0.260067979323589,"score_spread":0.2513623244657294,"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."}}