{"id":"W2956089214","doi":"10.1007/978-3-030-14078-6_5","title":"Text Mining the U.S. Congressional Record","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Key (lock); Word (group theory); Happiness; Linguistics; Population; Corpus linguistics; British National Corpus; Computer science; Natural language processing; Relation (database); Artificial intelligence; Psychology; Sociology; Social psychology; Demography; Data mining","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":[0.001270995,0.0002995686,0.0002463129,0.007239094,0.0009261682,0.003315671,0.0007827053,0.0005320434,0.01189612],"category_scores_gemma":[0.007073437,0.0001909428,0.0003241193,0.01052174,0.0005242847,0.002948933,0.0009139673,0.0006697707,0.008006958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009924944,"about_ca_system_score_gemma":0.001739618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01083492,"about_ca_topic_score_gemma":0.02631302,"domain_scores_codex":[0.9992502,0.0002098844,0.000100974,0.0001259773,0.0002780479,0.00003479358],"domain_scores_gemma":[0.9977455,0.001321482,0.000181687,0.0002510262,0.0004574936,0.0000428469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002958938,0.00001955045,0.003995651,0.0004468104,0.00002744838,0.0001087886,0.0006458923,0.000619672,0.001367735,0.03071737,0.3136544,0.6483672],"study_design_scores_gemma":[0.000005209675,0.00001541765,0.01459686,0.0005802091,0.0000360125,0.0003038759,0.001641504,0.00567331,0.003941351,0.02875777,0.9444212,0.00002736866],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.08208938,0.04573433,0.1044044,0.04009726,0.004018485,0.0004606111,0.2393451,0.006952387,0.4768981],"genre_scores_gemma":[0.2966612,0.02894604,0.199742,0.002107169,0.002077379,0.000409732,0.2564119,0.00178399,0.2118606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01189612,"threshold_uncertainty_score":0.03979653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04477826978886496,"score_gpt":0.3122159485279563,"score_spread":0.2674376787390914,"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."}}