{"id":"W2473556710","doi":"10.18653/v1/n16-1128","title":"Sentiment Composition of Words with Opposing Polarities","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Phrase; Polarity (international relations); Natural language processing; Computer science; Artificial intelligence; Composition (language); Sentiment analysis; Word (group theory); Word embedding; Association (psychology); Embedding; Linguistics; Psychology; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0001002208,0.0000563484,0.0000944507,0.00008204756,0.00004388198,0.00004882072,0.0001778315,0.00001324835,0.00008404641],"category_scores_gemma":[9.60415e-7,0.00003080969,0.0000368779,0.0001448952,0.00002911854,0.0003112325,0.00006569055,0.00001389735,0.0000112746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001422317,"about_ca_system_score_gemma":0.00001303101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001443628,"about_ca_topic_score_gemma":0.000002128798,"domain_scores_codex":[0.9994108,0.00002140599,0.0001321768,0.0001385611,0.0001953737,0.0001016916],"domain_scores_gemma":[0.999634,0.00003466317,0.00006374694,0.0001929031,0.00004469476,0.00003002312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000433427,0.0003170244,0.0566998,0.00002981656,0.0003567738,0.00001166007,0.002718206,0.0000706373,0.3193653,0.4693928,0.001313809,0.1496808],"study_design_scores_gemma":[0.002223806,0.0004718311,0.0146154,0.0006640886,0.00006707881,0.00002412918,0.0004871813,0.01763032,0.958652,0.001425972,0.003128456,0.0006097215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07365906,0.00004893843,0.9214528,0.001035689,0.00005554152,0.00003407269,4.733723e-7,0.00004085838,0.003672591],"genre_scores_gemma":[0.9261746,0.000005573508,0.07301175,0.00007171764,0.00001577235,0.000001036367,8.612874e-7,0.000002381902,0.0007162997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8525156,"threshold_uncertainty_score":0.1256383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460082972341539,"score_gpt":0.2365835206439686,"score_spread":0.2219826909205532,"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."}}