{"id":"W2773532513","doi":"10.26615/978-954-452-049-6_015","title":"Inter-Annotator Agreement in Sentiment Analysis: Machine Learning Perspective","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"","keywords":"Annotation; Computer science; Perspective (graphical); Artificial intelligence; Sentiment analysis; Reliability (semiconductor); Agreement; Natural language processing; Machine learning; Linguistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2303483,0.001761877,0.002398518,0.006258353,0.004654231,0.006826664,0.003177781,0.002645461,0.001920647],"category_scores_gemma":[0.4453475,0.001245243,0.001429639,0.006345012,0.00556569,0.008171546,0.007946665,0.003908028,0.001081757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003303593,"about_ca_system_score_gemma":0.003085321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0028968,"about_ca_topic_score_gemma":0.004482676,"domain_scores_codex":[0.6444675,0.2690283,0.02113199,0.02831319,0.03432436,0.00273456],"domain_scores_gemma":[0.3052136,0.5479997,0.04620592,0.03428536,0.0645433,0.00175203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003626487,0.001028106,0.253006,0.00729773,0.007312835,0.001265602,0.07610304,0.03121246,0.03929511,0.07133155,0.01984625,0.4886749],"study_design_scores_gemma":[0.0004666753,0.001215551,0.2061514,0.003347379,0.00226046,0.001529467,0.02026271,0.253198,0.06247741,0.3884393,0.05960491,0.00104673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1607456,0.004835604,0.8061408,0.002824821,0.0009447214,0.001626037,0.001247641,0.0007136595,0.02092108],"genre_scores_gemma":[0.7770953,0.0007852949,0.2132989,0.001138443,0.0006803366,0.002059142,0.001630644,0.0006969118,0.002614939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2303483,"threshold_uncertainty_score":0.9491175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254186839848775,"score_gpt":0.3058372293485844,"score_spread":0.2832953609500967,"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."}}