{"id":"W2950676070","doi":"10.48550/arxiv.1906.03677","title":"Happy Together: Learning and Understanding Appraisal From Natural\\n Language","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Embedding; Computer science; Sociality; Artificial intelligence; Agency (philosophy); Task (project management); Machine learning; Natural language processing; Focus (optics); Artificial neural network; Machine translation; Cognitive psychology; Psychology; Sociology; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005271212,0.000645209,0.0008041614,0.0004826036,0.0005555002,0.0007369213,0.00136518,0.0004199411,0.0004606975],"category_scores_gemma":[0.0001067612,0.0007491881,0.000445679,0.0008581615,0.0002303159,0.0007515952,0.002808403,0.001443982,0.0002605258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003469597,"about_ca_system_score_gemma":0.000149814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005905938,"about_ca_topic_score_gemma":0.00006314254,"domain_scores_codex":[0.9958917,0.0004554158,0.0004143183,0.002332602,0.0002494476,0.0006564871],"domain_scores_gemma":[0.9968989,0.001090147,0.0006638988,0.0009788015,0.00009820778,0.0002700224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004065168,0.0003960686,0.3119038,0.0003717633,0.004380539,0.001481538,0.03368583,0.3711739,0.002472179,0.261571,0.000694668,0.01146214],"study_design_scores_gemma":[0.0009277368,0.0000708253,0.001378958,0.0004028247,0.0003154744,0.00000393249,0.01200087,0.9809005,0.0001062883,0.001770741,0.001176905,0.0009449832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4797451,0.00171642,0.5127517,0.0001068384,0.002017251,0.0002385478,0.00001038407,0.0001497227,0.003264108],"genre_scores_gemma":[0.9917809,0.001150563,0.00112755,0.000065698,0.0002285115,2.906808e-7,0.00006269239,0.00003817758,0.005545557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6097266,"threshold_uncertainty_score":0.9994959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0777231234466074,"score_gpt":0.2242216538109689,"score_spread":0.1464985303643615,"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."}}