{"id":"W2760392765","doi":"10.18653/v1/d17-1056","title":"Refining Word Embeddings for Sentiment Analysis","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Treebank; Word2vec; Sentiment analysis; Word (group theory); Natural language processing; Artificial intelligence; Context (archaeology); Parsing; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0006764982,0.001336265,0.0005435007,0.001456536,0.0003098696,0.0007543931,0.0004688554,0.0005255713,0.003209107],"category_scores_gemma":[0.003893716,0.0002850178,0.0008051597,0.001250166,0.0003020208,0.003153665,0.0009376532,0.001163007,0.002731623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003805072,"about_ca_system_score_gemma":0.0004879596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452195,"about_ca_topic_score_gemma":0.002550578,"domain_scores_codex":[0.9994978,0.000125572,0.00006272569,0.0001646564,0.0001030881,0.0000462782],"domain_scores_gemma":[0.9991187,0.000222709,0.0001092945,0.0001668444,0.0003477436,0.00003457105],"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":[0.000356187,0.0002495649,0.007443051,0.0002742022,0.0001271436,0.0001252885,0.0004268932,0.01582173,0.04616515,0.008738087,0.01952667,0.900746],"study_design_scores_gemma":[0.00006387237,0.0003163761,0.005715633,0.00008420065,0.0001346223,0.0002735127,0.0005649499,0.9067731,0.0287171,0.03460322,0.02268379,0.00006965417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1383456,0.001106044,0.8474109,0.0005014366,0.0004548208,0.000297687,0.002016372,0.006087701,0.003779552],"genre_scores_gemma":[0.59065,0.0007706322,0.3934668,0.0002360325,0.0001706636,0.0003275265,0.008181259,0.000551394,0.005645738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003209107,"threshold_uncertainty_score":0.01073557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03981461137555894,"score_gpt":0.3329621635491202,"score_spread":0.2931475521735613,"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."}}