{"id":"W3168278108","doi":"10.1017/pan.2021.37","title":"Cross-Domain Topic Classification for Political Texts","year":2021,"lang":"en","type":"article","venue":"Political Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"H2020 European Research Council; University of Essex; Università Bocconi; Eidgenössische Technische Hochschule Zürich; Wissenschaftszentrum Berlin für Sozialforschung; York University; London School of Economics and Political Science","keywords":"Computer science; Classifier (UML); Domain (mathematical analysis); Artificial intelligence; Natural language processing; Labeled data; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01609405,0.001136573,0.001105122,0.008384028,0.001634625,0.003365829,0.001240072,0.001686829,0.002248029],"category_scores_gemma":[0.03532381,0.0003638859,0.001251805,0.004605992,0.001123123,0.003000078,0.002468018,0.002351138,0.001611406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001465748,"about_ca_system_score_gemma":0.0009550177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002408859,"about_ca_topic_score_gemma":0.002408343,"domain_scores_codex":[0.9903688,0.005652858,0.0005649994,0.001836879,0.001174248,0.0004021817],"domain_scores_gemma":[0.9542038,0.0344121,0.002274071,0.003971849,0.004387747,0.0007503316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00180432,0.001544241,0.08518912,0.0009282091,0.0008309933,0.0005330787,0.00323352,0.1425156,0.01454544,0.01548045,0.01677325,0.7166218],"study_design_scores_gemma":[0.00005132523,0.0001412428,0.01538309,0.00006976205,0.00006134583,0.0002076156,0.0008662455,0.9575075,0.007924411,0.01161626,0.006119051,0.00005215597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3617499,0.002473823,0.6189905,0.0007665396,0.0003785077,0.0006810228,0.002635963,0.003460733,0.008863056],"genre_scores_gemma":[0.8198316,0.0003105484,0.1701942,0.0001131599,0.000236993,0.0004322126,0.006234217,0.0002452258,0.002401843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01609405,"threshold_uncertainty_score":0.08511448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08141688647427724,"score_gpt":0.4642052680106769,"score_spread":0.3827883815363996,"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."}}