{"id":"W3124063403","doi":"10.1080/19331680802149640","title":"Automatic Annotation of Semantic Fields for Political Science Research","year":2008,"lang":"en","type":"article","venue":"Journal of Information Technology & Politics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Annotation; Computer science; Rhetorical question; Cluster analysis; Strengths and weaknesses; Politics; Artificial intelligence; Natural language processing; Semantic field; Information retrieval; Data science; Linguistics; Political science; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.001449626,0.00007338021,0.0001882363,0.002187148,0.0002448497,0.00005462432,0.001251853,0.0001612554,0.000001563638],"category_scores_gemma":[0.003050437,0.00006139599,0.00005330038,0.001128075,0.0007713695,0.002100576,0.0001725838,0.0003874594,0.000003016071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000200305,"about_ca_system_score_gemma":0.0009483128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008121049,"about_ca_topic_score_gemma":2.90642e-7,"domain_scores_codex":[0.9980946,0.00002386503,0.0007193501,0.00006920122,0.0006232124,0.0004697767],"domain_scores_gemma":[0.9960989,0.0002059735,0.000464124,0.0002896574,0.00284824,0.00009304153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002104875,0.00002376869,0.000211319,0.00007892409,0.000005388671,0.000003368697,0.0007063287,0.000003073158,0.0007133705,0.9884533,0.0003807936,0.009418285],"study_design_scores_gemma":[0.0003869069,0.00067539,0.0005824717,0.0001509023,0.000008014122,0.001068986,0.0005027661,0.02766017,0.2830637,0.6854625,0.0003211054,0.0001170829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2297057,0.0001157497,0.7643442,0.005163152,0.0001450603,0.0001648817,0.000002316117,0.0001369589,0.0002219134],"genre_scores_gemma":[0.6485012,0.000005768116,0.3513213,0.00013993,0.00002016912,0.000002957772,3.820903e-7,0.000001874128,0.000006520165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4187954,"threshold_uncertainty_score":0.3651879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02990937115205388,"score_gpt":0.3659734859193143,"score_spread":0.3360641147672604,"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."}}