{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009561155,0.00009603518,0.0002529683,0.0003045617,0.000145963,0.00009625952,0.0003127494,0.00004102771,0.000002506684],"category_scores_gemma":[0.0002283447,0.00008458168,0.00008488519,0.0003305579,0.0001235279,0.0006236479,0.000219029,0.0001028023,2.785089e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003269009,"about_ca_system_score_gemma":0.00002727646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001737836,"about_ca_topic_score_gemma":0.000006198939,"domain_scores_codex":[0.9989481,0.00007282992,0.0004946773,0.0001360889,0.0002163718,0.0001319634],"domain_scores_gemma":[0.9988577,0.00008014857,0.0006414282,0.0001790681,0.0002032001,0.0000384069],"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":[0.00001640058,0.00002319677,0.001639104,0.00001872138,0.00001536671,0.00001036324,0.0008405147,0.001425295,0.0001056478,0.008804823,0.00003421377,0.9870663],"study_design_scores_gemma":[0.002163514,0.001732248,0.08229946,0.0007851984,0.0006119906,0.0001260802,0.001035536,0.485156,0.04695399,0.3540295,0.02418589,0.0009205578],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1573841,0.0002327869,0.8419334,0.00001449252,0.0001521258,0.000045229,5.777319e-7,0.00001486367,0.0002223375],"genre_scores_gemma":[0.4199006,0.0001709197,0.5797989,0.00002904832,0.00008609795,3.755765e-7,6.602797e-8,0.000003060664,0.0000108712],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9861458,"threshold_uncertainty_score":0.3449141,"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."}}