{"id":"W4248291737","doi":"10.32920/ryerson.14641395","title":"Creating stochastic text data to solve privacy issues in social networking","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Social media; Recommender system; Weibull distribution; Data science; World Wide Web; Work (physics); Information privacy; Data modeling; Information retrieval; Internet privacy; Database; Engineering","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":[0.01996804,0.0008206485,0.0007376275,0.002369695,0.001635071,0.002419831,0.00223125,0.002575978,0.002209646],"category_scores_gemma":[0.09431206,0.0009030359,0.001380311,0.001958092,0.002292011,0.004719518,0.00283928,0.002822581,0.0009864278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00163895,"about_ca_system_score_gemma":0.001605088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002593352,"about_ca_topic_score_gemma":0.002742435,"domain_scores_codex":[0.9809653,0.01168278,0.0010686,0.002489686,0.003378612,0.0004150569],"domain_scores_gemma":[0.9066943,0.06715952,0.004121007,0.01681568,0.004499292,0.0007102008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001177689,0.001222702,0.0589824,0.0006202035,0.0004374235,0.001517969,0.003081787,0.586745,0.01950347,0.1320581,0.01571024,0.1789432],"study_design_scores_gemma":[0.00006930772,0.00009012128,0.001791881,0.00002363782,0.00001662235,0.0001944464,0.0001826851,0.9178526,0.007946011,0.06757235,0.004227296,0.00003299935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1424037,0.0001538446,0.8454024,0.001926306,0.0002459971,0.0006976857,0.00435462,0.002692554,0.00212297],"genre_scores_gemma":[0.5942839,0.0001231551,0.3953347,0.0006078001,0.0001466413,0.0009065014,0.006594589,0.0003201569,0.001682584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01996804,"threshold_uncertainty_score":0.1056024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1028478848182675,"score_gpt":0.3411414565524468,"score_spread":0.2382935717341793,"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."}}