{"id":"W2751358090","doi":"10.18653/v1/s17-2149","title":"UW-FinSent at SemEval-2017 Task 5: Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bigram; Computer science; SemEval; Task (project management); Sentiment analysis; Vectorization (mathematics); Paragraph; Artificial intelligence; Natural language processing; Machine learning; Baseline (sea); Regression; Training set; Simple (philosophy); World Wide Web; Statistics; Trigram","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":[0.005271656,0.002313199,0.001448182,0.002149429,0.001417125,0.002314799,0.001693884,0.001995778,0.01032933],"category_scores_gemma":[0.01325759,0.0006783618,0.001148843,0.001595695,0.0006201205,0.004063679,0.002746894,0.002846106,0.0167736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001621791,"about_ca_system_score_gemma":0.002202103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01769284,"about_ca_topic_score_gemma":0.02720528,"domain_scores_codex":[0.9970951,0.0009157085,0.0002411172,0.0008206792,0.0006119719,0.0003152821],"domain_scores_gemma":[0.993647,0.001580164,0.0002859936,0.001633414,0.002450764,0.0004026884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001173034,0.001034544,0.005432805,0.0008086217,0.0002071252,0.0005915157,0.0008981948,0.00313773,0.03333305,0.001400747,0.5578932,0.3940894],"study_design_scores_gemma":[0.0009982258,0.001778817,0.02580061,0.0004886076,0.0002968413,0.001077611,0.002154521,0.3294541,0.1606875,0.006156516,0.4707735,0.000333166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.2969086,0.003716525,0.1588461,0.00694021,0.007235805,0.00477437,0.1464341,0.3197414,0.05540288],"genre_scores_gemma":[0.2745349,0.0008238232,0.3134148,0.001682222,0.0008826869,0.00293901,0.3561817,0.005615241,0.04392568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01769284,"threshold_uncertainty_score":0.03517967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1307615376167965,"score_gpt":0.3725239434027842,"score_spread":0.2417624057859877,"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."}}