{"id":"W4396912905","doi":"10.48550/arxiv.2405.06692","title":"Analyzing Language Bias Between French and English in Conventional Multilingual Sentiment Analysis Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sentiment analysis; Linguistics; Computer science; Natural language processing; Artificial intelligence; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006408307,0.0003209554,0.0006038607,0.001716869,0.00008930988,0.0003378569,0.0007867683,0.0001832879,0.00004937026],"category_scores_gemma":[0.00002442466,0.0003647148,0.0005047868,0.002175528,0.00006408127,0.0002757763,0.002437983,0.0005796298,0.00001695956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001558076,"about_ca_system_score_gemma":0.0001016111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006670306,"about_ca_topic_score_gemma":0.0002191447,"domain_scores_codex":[0.9975365,0.0001755388,0.0004018709,0.001383195,0.0001715779,0.0003312993],"domain_scores_gemma":[0.9986418,0.0001632912,0.0002362064,0.0006802567,0.000124967,0.0001534313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000593846,0.0001173825,0.3369298,0.0001227512,0.003714148,0.0005847834,0.005279728,0.6234469,0.00001320506,0.02820796,0.00008492971,0.001492426],"study_design_scores_gemma":[0.0003339115,0.00001097167,0.008495946,0.0001083679,0.001063766,3.882696e-7,0.0004172046,0.9808488,0.00007644766,0.00824724,0.00001985171,0.0003770658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8519948,0.0005928128,0.1463453,0.00003299702,0.0002492689,0.0001288127,0.00002962291,0.0001219374,0.0005044836],"genre_scores_gemma":[0.9970651,0.00008288263,0.00169591,0.00001310275,0.0001167579,9.087037e-7,0.0001093634,0.00001244413,0.0009035878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3574019,"threshold_uncertainty_score":0.9998805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09082824059050736,"score_gpt":0.233674772441511,"score_spread":0.1428465318510037,"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."}}