{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005292309,0.0002665333,0.0004317207,0.0004211255,0.001402041,0.0009090215,0.001052259,0.00006927439,0.0001973479],"category_scores_gemma":[0.00006358445,0.000233369,0.0003118999,0.0003799087,0.00005424917,0.0008148947,0.0005743734,0.00009492967,0.0001313946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000150103,"about_ca_system_score_gemma":0.00007499436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004939871,"about_ca_topic_score_gemma":0.0005960608,"domain_scores_codex":[0.9975336,0.00008969812,0.0005180326,0.0007925648,0.0006496402,0.0004165208],"domain_scores_gemma":[0.997546,0.00006120404,0.000569268,0.00159875,0.00006545735,0.0001592942],"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":[0.0004411905,0.002160945,0.204162,0.0001177048,0.009288309,0.0005641242,0.01561558,0.1273046,0.06368431,0.0378558,0.2982006,0.2406048],"study_design_scores_gemma":[0.001300243,0.0001115901,0.02807326,0.00004845769,0.0007353657,0.000008453212,0.0002223776,0.9474975,0.006268951,0.0001893287,0.01489413,0.0006503508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6065885,0.00006121094,0.3875734,0.002852592,0.00116213,0.000314039,0.0001840107,0.0001155708,0.001148554],"genre_scores_gemma":[0.9601753,0.00003304648,0.03560176,0.001292019,0.0004135859,0.00001190772,0.0009912882,0.00001628122,0.001464791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8201929,"threshold_uncertainty_score":0.999898,"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."}}