{"id":"W4398198772","doi":"10.1057/s41599-024-03143-w","title":"Uncovering the essence of diverse media biases from the semantic embedding space","year":2024,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Media Influence and Politics","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Embedding; Space (punctuation); Semantic space; Computer science; Information retrieval; Artificial intelligence","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":[0.001917358,0.0004083498,0.0003491342,0.005822904,0.0005966608,0.002384564,0.0002234485,0.0004474336,0.001077064],"category_scores_gemma":[0.01434938,0.000179528,0.0002864414,0.004195419,0.001347628,0.004812463,0.002062993,0.0005250208,0.0002076119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004389754,"about_ca_system_score_gemma":0.0003114209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008113299,"about_ca_topic_score_gemma":0.001057782,"domain_scores_codex":[0.9986319,0.0006216409,0.0001259671,0.0002075913,0.0003079357,0.0001049255],"domain_scores_gemma":[0.9923241,0.00408688,0.001528555,0.0009097809,0.0009426838,0.0002079835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008118699,0.000239795,0.4959791,0.0008078318,0.0004884624,0.0006673727,0.01390273,0.01058594,0.02912971,0.1097861,0.003872891,0.3337282],"study_design_scores_gemma":[0.00005365551,0.0002978189,0.4592578,0.0004528924,0.0004088462,0.001162656,0.01873278,0.1872195,0.01909135,0.2916964,0.02143798,0.0001882714],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9338302,0.0009735313,0.05918711,0.0003594309,0.00004181647,0.0000411425,0.0007055406,0.0001101078,0.00475104],"genre_scores_gemma":[0.9940559,0.0001508833,0.005335049,0.0000173473,0.00002766185,0.00001439941,0.0002509143,0.0000114986,0.0001363732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005822904,"threshold_uncertainty_score":0.01014012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2474867723768657,"score_gpt":0.3985911976583965,"score_spread":0.1511044252815308,"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."}}