{"id":"W2806067301","doi":"","title":"Target Focused Sentiment Extraction Framework.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Extraction (chemistry); Computer science; Sentiment analysis; Data science; Natural language processing; Chemistry; Chromatography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001540643,0.001203192,0.0008668103,0.003609276,0.0008205633,0.002257117,0.0009927659,0.001155225,0.009660386],"category_scores_gemma":[0.004126333,0.0003811616,0.001069825,0.002755123,0.0003071943,0.002847323,0.001716402,0.001423453,0.01284754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007002471,"about_ca_system_score_gemma":0.001183975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001952219,"about_ca_topic_score_gemma":0.003751535,"domain_scores_codex":[0.9988819,0.0002914558,0.00009376325,0.0002807317,0.0003453052,0.0001069513],"domain_scores_gemma":[0.9988045,0.0003271675,0.00009759313,0.0001446489,0.0005606812,0.00006542489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000361601,0.000247737,0.00340033,0.001233421,0.0002587447,0.0003201107,0.0009907185,0.002491279,0.03855663,0.04430466,0.2172632,0.6905716],"study_design_scores_gemma":[0.0001243542,0.0003118335,0.01203741,0.0004947467,0.0004954662,0.00133,0.001450026,0.2912488,0.04899576,0.1134144,0.5299545,0.0001427586],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01549035,0.002975047,0.9107822,0.001786855,0.001137358,0.001101056,0.01531391,0.01053525,0.040878],"genre_scores_gemma":[0.2631286,0.002558309,0.6296121,0.001199473,0.001365045,0.00183223,0.05029784,0.00135895,0.04864741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009660386,"threshold_uncertainty_score":0.03231722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01503293188210018,"score_gpt":0.2846347443300141,"score_spread":0.2696018124479139,"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."}}