{"id":"W2786269463","doi":"10.3390/jrfm11010008","title":"Estimation of Cross-Lingual News Similarities Using Text-Mining Methods","year":2018,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Similarity (geometry); Natural language processing; Artificial intelligence; Word (group theory); Information retrieval; Task (project management); The Internet; World Wide Web; Image (mathematics); Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.002886921,0.001061167,0.001116659,0.009321133,0.0008162822,0.001734499,0.001426602,0.00110845,0.00129386],"category_scores_gemma":[0.01242166,0.0004523863,0.001321748,0.006281033,0.0004315902,0.003933813,0.001305589,0.0009191993,0.001315547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005508651,"about_ca_system_score_gemma":0.00074314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001902852,"about_ca_topic_score_gemma":0.00270275,"domain_scores_codex":[0.9961281,0.0008635675,0.0006630408,0.001369159,0.0007969521,0.0001791005],"domain_scores_gemma":[0.9915994,0.004096176,0.001266927,0.00072067,0.002149948,0.0001668557],"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":[0.0006854105,0.0007428859,0.05737223,0.0006887497,0.0008233401,0.001021243,0.0009527793,0.03738548,0.01903635,0.005634214,0.004815427,0.8708419],"study_design_scores_gemma":[0.00006304165,0.0002295637,0.02664697,0.00006108783,0.0002766649,0.0008294902,0.0008338565,0.9383366,0.01673703,0.009145886,0.006747639,0.00009218352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2159404,0.001533141,0.7749548,0.0002868334,0.0001979011,0.0003226238,0.001698868,0.001432624,0.003632797],"genre_scores_gemma":[0.6389796,0.0005475751,0.3524143,0.0001185799,0.0003409465,0.0003757328,0.004869366,0.0001567336,0.002197177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009321133,"threshold_uncertainty_score":0.01526767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0254576792545957,"score_gpt":0.3778261132054529,"score_spread":0.3523684339508572,"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."}}