{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006741254,0.0002211157,0.0003252533,0.0001614728,0.0001968603,0.001234312,0.002693377,0.00020764,0.00003050293],"category_scores_gemma":[0.0002193389,0.0002377023,0.00005610202,0.0004735994,0.00001306957,0.0004100103,0.01076472,0.0006268453,0.00001824399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001113714,"about_ca_system_score_gemma":0.0001727221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001604421,"about_ca_topic_score_gemma":0.0006562117,"domain_scores_codex":[0.9978307,0.00007700066,0.0003367023,0.001077616,0.0003336188,0.0003443286],"domain_scores_gemma":[0.9981468,0.0001527409,0.0001262193,0.001436897,0.00006564059,0.00007167165],"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":[0.00004208454,0.0003650764,0.001525756,0.0004000838,0.0002431948,0.0001825102,0.08994295,0.1344441,0.0008815735,0.01246395,0.03116874,0.72834],"study_design_scores_gemma":[0.0002335945,0.00004040964,0.004451083,0.0007603277,0.00002098498,0.00001046597,0.0003672237,0.9839506,0.0001158142,0.005196643,0.004050223,0.0008026187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009581254,0.0003307356,0.9836638,0.00183971,0.002345758,0.0002670322,0.000002958149,0.0002433169,0.001725447],"genre_scores_gemma":[0.8374655,0.00001472668,0.1585407,0.0004740019,0.003121995,0.00003263553,0.00007726553,0.00002412159,0.0002491015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8495066,"threshold_uncertainty_score":0.9998025,"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."}}