{"id":"W4405430877","doi":"10.2139/ssrn.5022797","title":"Righting the Writers: Assessing Bias in Wikipedia's Political Content -An Event Study and Sentiment Analysis ","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; University of British Columbia","funders":"","keywords":"Politics; Content (measure theory); Event (particle physics); Content analysis; Sentiment analysis; Psychology; Political science; Natural language processing; Computer science; Law; Social science; Sociology; Mathematics","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":[0.00647744,0.0001927995,0.0002977869,0.001890849,0.001122643,0.001781483,0.0003305798,0.0005077353,0.001721501],"category_scores_gemma":[0.03289944,0.0001347993,0.0002425927,0.001950554,0.0006545488,0.001784291,0.001290167,0.0005973427,0.0004165882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004823867,"about_ca_system_score_gemma":0.0003167082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001724927,"about_ca_topic_score_gemma":0.002855821,"domain_scores_codex":[0.9962495,0.001954037,0.0004223121,0.000384012,0.0008288483,0.0001612457],"domain_scores_gemma":[0.9564611,0.02534282,0.01125507,0.00157884,0.004248648,0.001113478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001218639,0.0004699256,0.8876196,0.0002992443,0.0001740462,0.0002105381,0.03313553,0.0002628235,0.01296273,0.00244607,0.004125287,0.05707557],"study_design_scores_gemma":[0.00004184117,0.0002701501,0.9561607,0.00007690222,0.0001426217,0.000270314,0.02296012,0.003131596,0.00784712,0.001581444,0.007471045,0.00004615865],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954962,0.00005775153,0.001023223,0.0001253877,0.00003701389,0.00004455455,0.0002933385,0.00001228148,0.002910327],"genre_scores_gemma":[0.9968065,0.00004034604,0.001369025,0.0000692644,0.00004729177,0.00008041617,0.0004113797,0.00002468471,0.001151132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00647744,"threshold_uncertainty_score":0.0342564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09020071076757745,"score_gpt":0.4269840104503309,"score_spread":0.3367832996827534,"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."}}