{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002306637,0.0007287751,0.001136076,0.004817311,0.001815454,0.001745242,0.0008662393,0.0007229435,0.003786342],"category_scores_gemma":[0.0075909,0.0004119286,0.001655081,0.004179657,0.0004633993,0.001793647,0.001201811,0.001579557,0.002420297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162656,"about_ca_system_score_gemma":0.001947594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008263696,"about_ca_topic_score_gemma":0.0129264,"domain_scores_codex":[0.997993,0.0006919741,0.0002683236,0.0003170992,0.0004623508,0.00026734],"domain_scores_gemma":[0.9957783,0.002277432,0.000351004,0.0003857576,0.001017735,0.0001896181],"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":[0.0005705438,0.0009437624,0.01893856,0.0005662933,0.0003145957,0.0002190862,0.0007178513,0.01664422,0.02339719,0.01224765,0.01743571,0.9080045],"study_design_scores_gemma":[0.0001033647,0.0003912992,0.02269649,0.0001425171,0.0003743287,0.0002128849,0.0006626224,0.8946885,0.01808367,0.05106751,0.01149685,0.00007996282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.113055,0.00178036,0.8711863,0.0008793802,0.0003105304,0.0008967855,0.002802379,0.003311127,0.005778259],"genre_scores_gemma":[0.4263814,0.0006225641,0.5607311,0.0003103852,0.0003607876,0.0007674015,0.005403957,0.0002647194,0.005157643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008263696,"threshold_uncertainty_score":0.01643121,"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."}}