{"id":"W1055035554","doi":"10.1007/s00500-015-1812-4","title":"Hierarchical classification in text mining for sentiment analysis of online news","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Sentiment analysis; Class (philosophy); Task (project management); Artificial intelligence; Binary classification; Polarity (international relations); Tone (literature); Data mining; Information retrieval; Natural language processing; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000756172,0.0001073121,0.0003493857,0.0006563188,0.00006061768,0.00006732216,0.0004189512,0.0000453402,0.000003788884],"category_scores_gemma":[0.0001324248,0.0001051831,0.0001855515,0.001850053,0.00002406588,0.0001288527,0.0001807183,0.00007334213,0.000002097942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005525522,"about_ca_system_score_gemma":0.00006029174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005503759,"about_ca_topic_score_gemma":0.00008632323,"domain_scores_codex":[0.9984617,0.00008101708,0.0005593232,0.0003774811,0.000288665,0.0002318669],"domain_scores_gemma":[0.9988669,0.000320095,0.0002719043,0.0003243278,0.000130864,0.00008593572],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002926411,0.0005574718,0.4438206,0.00002912102,0.0008324428,0.000003640514,0.008712173,0.09120459,0.001131072,0.0138898,0.0007828948,0.439007],"study_design_scores_gemma":[0.0004040714,0.00003729834,0.03967666,0.00002429134,0.00008740885,3.519869e-7,0.0008227239,0.9582358,0.0001128448,0.000163284,0.0003296571,0.0001055901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3984741,0.00006418862,0.6005479,0.0005067243,0.0001245781,0.00008762399,0.000001712418,0.00003290621,0.0001603703],"genre_scores_gemma":[0.8589424,0.000001164691,0.1408278,0.00008542681,0.0000645681,0.000002260037,0.00004011952,0.000005123638,0.00003116769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8670312,"threshold_uncertainty_score":0.4289241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07647598286024078,"score_gpt":0.3373545197430311,"score_spread":0.2608785368827903,"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."}}