{"id":"W2908347907","doi":"10.4000/books.aaccademia.4620","title":"UNIBA - Integrating distributional semantics features in a supervised approach for detecting irony in Italian tweets","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Task (project management); Irony; Computer science; Artificial intelligence; Constraint (computer-aided design); Natural language processing; Representation (politics); Semantics (computer science); Polarity (international relations); Distributional semantics; Machine learning; Information retrieval; Semantic similarity; Linguistics; Mathematics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004115771,0.0004526639,0.0005783889,0.0005594972,0.0001953018,0.00009274439,0.001864872,0.0008314977,0.000003005602],"category_scores_gemma":[0.00008884267,0.0005170804,0.0002292426,0.00007675538,0.0001910899,0.0004464707,0.001003389,0.001240579,7.580271e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006636884,"about_ca_system_score_gemma":0.0001312091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001579094,"about_ca_topic_score_gemma":0.0002041441,"domain_scores_codex":[0.9977802,0.00007275902,0.0003984075,0.0009297648,0.0003372868,0.0004815534],"domain_scores_gemma":[0.9984682,0.000255665,0.0003502659,0.0006478128,0.0001735134,0.0001045916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007397577,0.0000429437,0.000276725,0.0001941052,0.00013143,0.0001008909,0.001948368,0.0001141251,0.0003791951,0.9851597,0.0009501399,0.01062841],"study_design_scores_gemma":[0.009979054,0.0008860788,0.001275038,0.005195924,0.0009019024,0.0001544217,0.002340785,0.2263527,0.02377133,0.1803815,0.5388933,0.009867919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000708804,0.0001198155,0.7479243,0.00006166791,0.00007105458,0.001119938,0.0001048303,0.0003944078,0.2494952],"genre_scores_gemma":[0.1871872,0.00007745314,0.4602839,0.0001909221,0.0003522183,0.00003036862,0.0004490061,0.0001511207,0.3512778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8047782,"threshold_uncertainty_score":0.9997281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02536097255689939,"score_gpt":0.2485929089907684,"score_spread":0.223231936433869,"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."}}