{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003379038,0.0009980648,0.0008003631,0.01088201,0.00341129,0.001898456,0.001075977,0.001921803,0.01125415],"category_scores_gemma":[0.0225212,0.0004128831,0.0004529581,0.01390172,0.001389081,0.001758042,0.002812673,0.001290797,0.007974826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002502727,"about_ca_system_score_gemma":0.004115975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02307373,"about_ca_topic_score_gemma":0.04060939,"domain_scores_codex":[0.9933882,0.002102099,0.0009297793,0.0009860391,0.002172765,0.0004211104],"domain_scores_gemma":[0.97713,0.01106987,0.002007917,0.001314965,0.007601507,0.000875668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000695024,0.0004813217,0.01675139,0.008363558,0.0000801545,0.002996758,0.0438268,0.0007939021,0.01229838,0.008675121,0.6836014,0.2214362],"study_design_scores_gemma":[0.0001045752,0.00008086271,0.05490683,0.001247163,0.00004469753,0.0007618596,0.01243681,0.00133775,0.003713698,0.001502118,0.9237455,0.0001181256],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1532896,0.003813377,0.01266082,0.002060849,0.001409166,0.002846372,0.7849947,0.001377641,0.03754748],"genre_scores_gemma":[0.1689098,0.0020045,0.03794627,0.000595154,0.0006775719,0.01130078,0.7562013,0.0009765138,0.02138819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02307373,"threshold_uncertainty_score":0.04587889,"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."}}