{"id":"W2983553948","doi":"10.1007/s41701-019-00065-w","title":"The SFU Opinion and Comments Corpus: A Corpus for the Analysis of Online News Comments","year":2019,"lang":"en","type":"article","venue":"Corpus Pragmatics","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University; Nvidia","keywords":"Computer science; Corpus linguistics; Focus (optics); Meaning (existential); Newspaper; Negation; Linguistics; Constructive; Interpretation (philosophy); Annotation; Natural language processing; Artificial intelligence; Psychology; Process (computing); Sociology; Media studies","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005942211,0.0001710585,0.0003177456,0.0001164672,0.0003581258,0.0001966658,0.0008572551,0.00007263638,0.000004212741],"category_scores_gemma":[0.0001423694,0.0001051022,0.0001420343,0.0007229765,0.00008691279,0.0001611382,0.0002969687,0.0001539785,0.000009539275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003910881,"about_ca_system_score_gemma":0.00004741317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009558499,"about_ca_topic_score_gemma":0.0001618012,"domain_scores_codex":[0.9985368,0.0001188558,0.0004641136,0.0002602881,0.0003362112,0.0002837253],"domain_scores_gemma":[0.9970734,0.001285067,0.0004554805,0.0009467033,0.0001638232,0.00007548882],"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":[0.0001992742,0.0006112254,0.05475537,0.0002585016,0.002745102,0.000002250873,0.00289787,0.001734477,0.001435037,0.02350848,0.009122631,0.9027297],"study_design_scores_gemma":[0.001760254,0.0005349913,0.0279927,0.00009561893,0.0005038737,0.00001140825,0.0004920302,0.8316038,0.0009477969,0.002786022,0.1329404,0.0003310854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4410268,0.002796414,0.5375487,0.01046362,0.004409238,0.003053362,0.0001513725,0.0001936213,0.0003569226],"genre_scores_gemma":[0.9582819,0.004210837,0.03187308,0.003831039,0.000181474,0.0001474466,0.0001402689,0.00005424596,0.001279733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9023987,"threshold_uncertainty_score":0.4285944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01791365588722305,"score_gpt":0.2736738631037269,"score_spread":0.2557602072165039,"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."}}