{"id":"W2488625897","doi":"10.4018/978-1-5225-0463-4.ch009","title":"Automated Identification of Child Abuse in Chat Rooms by Using Data Mining","year":2016,"lang":"en","type":"book-chapter","venue":"Advances in data mining and database management book series","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"","keywords":"Preprocessor; Identification (biology); Computer science; Data pre-processing; Domain (mathematical analysis); Data mining; Data science; Feature extraction; Scalability; Social media; Machine learning; Artificial intelligence; World Wide Web; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.001022353,0.0009206714,0.0008573278,0.00389641,0.0005565014,0.002276018,0.001304771,0.001036567,0.001780252],"category_scores_gemma":[0.004067357,0.0004033713,0.0008346635,0.003717872,0.0002973452,0.002031622,0.0008977229,0.001073946,0.003016274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005351962,"about_ca_system_score_gemma":0.0006221223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001320321,"about_ca_topic_score_gemma":0.002579698,"domain_scores_codex":[0.9991825,0.0001327454,0.00008354247,0.0001845424,0.0003683111,0.00004836068],"domain_scores_gemma":[0.9980575,0.001002262,0.0002624062,0.0001924342,0.000427223,0.00005805151],"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":[0.0000673303,0.0001985301,0.01993822,0.0009040271,0.00008707324,0.0006793255,0.0005322105,0.003607439,0.008332296,0.004356879,0.05345543,0.9078413],"study_design_scores_gemma":[0.00004281951,0.0003768762,0.08253133,0.002332977,0.0003516546,0.006852739,0.003770022,0.316742,0.0756409,0.06196055,0.4491493,0.0002488685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2057604,0.05119115,0.6076027,0.0103494,0.002207032,0.001624806,0.02171816,0.01117339,0.08837305],"genre_scores_gemma":[0.2439993,0.02740919,0.667608,0.001545062,0.0008870097,0.0006723055,0.02605339,0.0004705685,0.03135518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00389641,"threshold_uncertainty_score":0.005955517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03144693544285009,"score_gpt":0.2802886728559151,"score_spread":0.248841737413065,"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."}}