{"id":"W2464521204","doi":"10.18653/v1/s16-1004","title":"SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Phrase; Task (project management); Artificial intelligence; SemEval; Arabic; Word (group theory); Domain (mathematical analysis); 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":[0.003759319,0.004549904,0.002120137,0.003448822,0.001653443,0.002564608,0.002192284,0.003365498,0.01448078],"category_scores_gemma":[0.01204921,0.0005971683,0.002017925,0.00191079,0.0008239913,0.004462836,0.005154361,0.002567571,0.02021077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001252485,"about_ca_system_score_gemma":0.001669334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004447782,"about_ca_topic_score_gemma":0.008317021,"domain_scores_codex":[0.9961153,0.001029717,0.0004850006,0.001236788,0.0007758947,0.0003573455],"domain_scores_gemma":[0.9932869,0.00231212,0.0003354399,0.00156796,0.001947735,0.0005498807],"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":[0.001954817,0.001114335,0.01316465,0.002956422,0.0005334893,0.00117645,0.00121542,0.003692611,0.05203575,0.001527392,0.4972045,0.4234241],"study_design_scores_gemma":[0.00138442,0.002101949,0.07159308,0.0007893913,0.0007054752,0.00434777,0.005186663,0.2342917,0.191496,0.0117635,0.4757,0.0006400982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4639881,0.006562969,0.1015364,0.002993347,0.005170977,0.0041162,0.2321031,0.1258306,0.05769835],"genre_scores_gemma":[0.2921462,0.000702187,0.2034678,0.001403408,0.0006794985,0.002805098,0.4668465,0.004402355,0.0275469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01448078,"threshold_uncertainty_score":0.04844308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437407673724674,"score_gpt":0.2347434297953175,"score_spread":0.2203693530580708,"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."}}