{"id":"W2954211942","doi":"10.1017/pan.2019.26","title":"Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora","year":2019,"lang":"en","type":"article","venue":"Political Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":165,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Ideology; Metadata; Parliament; Computer science; Context (archaeology); Politics; Word (group theory); Natural language processing; Language model; Linguistics; Artificial intelligence; Data science; Sociology; Political science; World Wide Web; Law; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001867207,0.0001073115,0.0006255668,0.0006880751,0.0001339763,0.00003632222,0.0003053385,0.00006713858,0.002971638],"category_scores_gemma":[0.0003549925,0.00007271509,0.0009514176,0.0049555,0.0002635733,0.00006072969,0.00006355239,0.00009093471,0.00001247374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329862,"about_ca_system_score_gemma":0.00006294303,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01311325,"about_ca_topic_score_gemma":0.008319763,"domain_scores_codex":[0.997936,0.0003328713,0.0004899523,0.0003005651,0.000512365,0.0004282832],"domain_scores_gemma":[0.9957979,0.003569937,0.0001437199,0.000211132,0.0001444224,0.00013294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004668024,0.0001525012,0.6167433,0.000006253571,0.007426981,9.622667e-7,0.0007421725,0.0239499,0.00001149165,0.3470255,0.00006010291,0.003834141],"study_design_scores_gemma":[0.0004017786,0.00004844732,0.6224132,0.000005960657,0.02188396,6.712597e-8,0.008680864,0.3015081,0.00002782479,0.04095277,0.003826772,0.0002502849],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9429736,0.0001336416,0.04617698,0.006420952,0.00007011883,0.0003423429,0.00004300031,0.00002145771,0.003817872],"genre_scores_gemma":[0.9960397,0.00001117648,0.002475505,0.0005110274,0.00005417972,0.00003108749,0.00004739685,0.000003367989,0.0008265743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3060727,"threshold_uncertainty_score":0.9979398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0491700587411518,"score_gpt":0.3975014255878185,"score_spread":0.3483313668466667,"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."}}