{"id":"W2964321678","doi":"10.3115/v1/w14-2614","title":"Credibility Adjusted Term Frequency: A Supervised Term Weighting Scheme for Sentiment Analysis and Text Classification","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Weighting; Term (time); Computer science; Credibility; Scheme (mathematics); Baseline (sea); Sentiment analysis; Artificial intelligence; Data mining; Pattern recognition (psychology); Machine learning; Information retrieval; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001350511,0.0004608577,0.0008862427,0.0007462978,0.0002772317,0.0008476007,0.001118105,0.0003196529,0.0001500986],"category_scores_gemma":[0.00008131735,0.0004076964,0.0006834108,0.0007845799,0.00007237813,0.0002914564,0.001134753,0.0002987315,0.00001354617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001288058,"about_ca_system_score_gemma":0.0001119229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105561,"about_ca_topic_score_gemma":0.00005541841,"domain_scores_codex":[0.9960294,0.0001838564,0.0009939304,0.001827098,0.0005188425,0.0004469033],"domain_scores_gemma":[0.9967076,0.000256818,0.0006242526,0.001860393,0.00034592,0.0002050433],"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":[0.00003189934,0.000532788,0.8502949,0.0008742172,0.006678357,0.000003880094,0.002484012,0.000255612,0.02283482,0.02169754,0.00125423,0.09305777],"study_design_scores_gemma":[0.0004359728,0.00003028467,0.148479,0.00006527578,0.0007668452,6.579085e-7,0.00005931456,0.8470917,0.001412264,0.001116627,0.00008581085,0.0004562007],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2784692,0.0001841041,0.718442,0.0008653841,0.0002684452,0.0006418854,0.00001479716,0.0002087117,0.0009054795],"genre_scores_gemma":[0.7520547,0.0000354265,0.2465519,0.0001505661,0.0001910041,0.0001594809,0.0003486175,0.00001888555,0.0004894348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8468361,"threshold_uncertainty_score":0.9998375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05371121589205208,"score_gpt":0.3002124657119668,"score_spread":0.2465012498199147,"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."}}