{"id":"W2274912527","doi":"10.1613/jair.4787","title":"How Translation Alters Sentiment","year":2016,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; National Research Council Canada","funders":"","keywords":"Sentiment analysis; Computer science; Focus (optics); Lexicon; Natural language processing; Annotation; Artificial intelligence; Arabic; Machine translation; Linguistics; Social media; Resource (disambiguation); World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003293506,0.00008220005,0.0001684346,0.0006114721,0.0001498688,0.0004708143,0.0008231121,0.0000435983,0.00008524885],"category_scores_gemma":[0.0001819932,0.00005036455,0.0001741351,0.000752169,0.000105115,0.0009951501,0.00008202228,0.000198766,0.00008576074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008668641,"about_ca_system_score_gemma":0.0001098643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004070282,"about_ca_topic_score_gemma":0.000003921489,"domain_scores_codex":[0.9974611,0.0002637291,0.0004868188,0.0001963717,0.001241912,0.0003500736],"domain_scores_gemma":[0.9982612,0.0004569554,0.0002005175,0.0002601817,0.0006658839,0.0001553226],"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":[0.00002361289,0.00007050196,0.00009852061,0.000002997753,0.0000399631,0.00002221408,0.0005662635,0.00004790208,0.06834627,0.02191521,0.0004509054,0.9084156],"study_design_scores_gemma":[0.00013482,0.0007634017,0.0001254693,0.0002515013,0.00001725935,0.00004804167,0.001621605,0.04623342,0.8775336,0.05621316,0.01678928,0.0002684286],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01831877,0.0002756595,0.957945,0.02277,0.0003952751,0.00006951723,3.449772e-7,0.000009635021,0.0002158102],"genre_scores_gemma":[0.9793816,0.0002664197,0.01955865,0.00002499542,0.0003636738,0.000001556684,1.564297e-7,0.00000605592,0.0003969576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9610628,"threshold_uncertainty_score":0.4540073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2633291444881119,"score_gpt":0.4243514885302698,"score_spread":0.1610223440421579,"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."}}