{"id":"W2904391139","doi":"10.1109/access.2018.2885117","title":"Sentiment Identification in Football-Specific Tweets","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Football; Sentiment analysis; Computer science; Popularity; Lexicon; Classifier (UML); Social media; Artificial intelligence; Identification (biology); Feeling; Natural language processing; Data science; World Wide Web; Psychology; History","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":[],"consensus_categories":[],"category_scores_codex":[0.0003645682,0.00009775618,0.0001240528,0.0002547951,0.00009721832,0.0006227648,0.001181075,0.00003711633,0.0001084454],"category_scores_gemma":[0.000005369984,0.00009492182,0.00005434137,0.0007935176,0.00003572742,0.0009662447,0.0001715506,0.00005933427,0.0004307378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004817643,"about_ca_system_score_gemma":0.00001674095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002987693,"about_ca_topic_score_gemma":0.00002616274,"domain_scores_codex":[0.9986948,0.00004858858,0.0003229707,0.0004151805,0.0002974268,0.0002210545],"domain_scores_gemma":[0.9991665,0.00002811375,0.0001253841,0.0005421683,0.00008754688,0.00005031141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005987326,0.001425594,0.2837058,0.00005896193,0.0003045033,0.0001046055,0.009625653,0.001027871,0.1176074,0.05845201,0.1567853,0.3708425],"study_design_scores_gemma":[0.001544379,0.0001122359,0.439325,0.0001195068,0.00002265684,0.000008391702,0.0001162992,0.1254912,0.369359,0.006757449,0.0561954,0.0009484368],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6091299,0.0001683595,0.3836902,0.0007896627,0.002239484,0.000170548,6.076083e-7,0.0001042697,0.003706988],"genre_scores_gemma":[0.9977422,0.00003065517,0.001399323,0.0001715964,0.00025753,0.00001264645,0.00000340371,0.000005869434,0.0003767633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3886123,"threshold_uncertainty_score":0.6005335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05307631494144845,"score_gpt":0.3389338855961466,"score_spread":0.2858575706546982,"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."}}