{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01279847,0.0006470374,0.0006826743,0.01434606,0.00330615,0.004388974,0.001417839,0.001256899,0.006671408],"category_scores_gemma":[0.04833902,0.0005251609,0.0005364078,0.009254538,0.001847269,0.004753877,0.003653521,0.00193694,0.003031996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002571641,"about_ca_system_score_gemma":0.004467515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002453751,"about_ca_topic_score_gemma":0.005542227,"domain_scores_codex":[0.9848104,0.009628035,0.0009590905,0.001260582,0.003031712,0.0003100979],"domain_scores_gemma":[0.9140298,0.05025488,0.005069146,0.01273485,0.01694761,0.0009636834],"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":[0.0004912938,0.0004297955,0.01693654,0.001790861,0.00006058393,0.0003027296,0.008596601,0.005517827,0.06668431,0.09136332,0.04962422,0.7582019],"study_design_scores_gemma":[0.000200011,0.0001539172,0.0362795,0.0009307882,0.0001105659,0.0008099313,0.008525072,0.2005652,0.1230744,0.1963498,0.4327188,0.0002820421],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09019123,0.001129038,0.8547144,0.003802924,0.0005869871,0.001183623,0.007386555,0.009284416,0.03172089],"genre_scores_gemma":[0.18411,0.0003074956,0.8012519,0.0001731174,0.0001563581,0.0011719,0.008197454,0.000722952,0.003908773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01434606,"threshold_uncertainty_score":0.0676856,"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."}}