{"id":"W2740540254","doi":"10.18653/v1/s17-1007","title":"Emotion Intensities in Tweets","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sadness; Anger; Consistency (knowledge bases); Computer science; Benchmark (surveying); Task (project management); Annotation; Emotion classification; Natural language processing; Word (group theory); Emotion detection; Artificial intelligence; Scaling; Emotion recognition; Cognitive psychology; Psychology; Social psychology; Linguistics; Mathematics","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":[0.0009138845,0.000773158,0.0004448854,0.002523562,0.00047139,0.001432829,0.0003739935,0.0005693714,0.002517884],"category_scores_gemma":[0.008760129,0.0002156663,0.0005417557,0.00200068,0.0003211204,0.001540548,0.0008516711,0.0008777425,0.001685701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005131527,"about_ca_system_score_gemma":0.0001697921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001247782,"about_ca_topic_score_gemma":0.001434433,"domain_scores_codex":[0.9985147,0.0002990653,0.0001413454,0.0003861228,0.000533728,0.0001251103],"domain_scores_gemma":[0.9957033,0.0020357,0.0009790203,0.0002863314,0.0008364459,0.0001591824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003034435,0.000537662,0.4308413,0.002027224,0.0005861807,0.0007681876,0.003758613,0.009379675,0.1480346,0.004450729,0.04215884,0.3544225],"study_design_scores_gemma":[0.00006842866,0.0004868284,0.8008993,0.0001989752,0.0002703344,0.001353092,0.002860933,0.06909406,0.06044473,0.008458052,0.05565564,0.00020975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.911326,0.001096048,0.03258199,0.0009214332,0.000413697,0.0003040207,0.03935217,0.001420294,0.01258433],"genre_scores_gemma":[0.9428962,0.0004444979,0.02429855,0.0001686594,0.0004090136,0.0003395476,0.02786724,0.0002044022,0.003371974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002523562,"threshold_uncertainty_score":0.00842315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05343004542447813,"score_gpt":0.3076609485486365,"score_spread":0.2542309031241583,"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."}}