{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009600089,0.0003459243,0.0004013888,0.0004869477,0.0001325726,0.0001949317,0.002563986,0.0001029852,0.00001185537],"category_scores_gemma":[0.00005883225,0.0003418155,0.00001711343,0.0001553117,0.0001682163,0.01224376,0.00354947,0.0001464905,0.000004127626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004931907,"about_ca_system_score_gemma":0.0000203642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000261648,"about_ca_topic_score_gemma":0.0003050921,"domain_scores_codex":[0.9971533,0.00004831041,0.0007633158,0.001379403,0.0003709373,0.0002846684],"domain_scores_gemma":[0.9954158,0.0001136781,0.0005977835,0.003794507,0.0000264695,0.0000517474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003605864,0.0002312222,0.0009162803,0.003606112,0.0004286997,0.0004573793,0.002627933,0.0002700725,0.0005722881,0.05702466,0.03370172,0.899803],"study_design_scores_gemma":[0.0009121393,0.00005946095,0.00006796802,0.005664516,0.0001017452,0.0000346461,0.0002536889,0.08201925,0.0002118645,0.0004465904,0.9093439,0.0008842137],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004204188,0.2352568,0.4888372,0.002547351,0.009189454,0.005690269,0.05239641,0.003160659,0.1987176],"genre_scores_gemma":[0.01244923,0.4435278,0.3575862,0.001276004,0.0008269624,0.000133624,0.07350799,0.0004757365,0.1102165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8989188,"threshold_uncertainty_score":0.9999034,"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."}}