{"id":"W4387895505","doi":"10.54254/2755-2721/21/20231143","title":"An overview of big data mining and data privacy protection technologies","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"La Cité Collégiale","funders":"","keywords":"Computer science; Information privacy; Privacy protection; Big data; Data Protection Act 1998; Privacy by Design; Privacy software; Computer security; Personally identifiable information; Association rule learning; Internet privacy; Data anonymization; Data science; Data mining","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003628029,0.0001141191,0.0001412144,0.0002208703,0.00006643703,0.0000889687,0.009526116,0.0000683905,2.219589e-7],"category_scores_gemma":[0.001098999,0.0001168743,0.000005051241,0.0006581478,0.00005387394,0.0005812401,0.05428843,0.0001052587,0.000001257928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007968353,"about_ca_system_score_gemma":0.00002488748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000679391,"about_ca_topic_score_gemma":6.875501e-7,"domain_scores_codex":[0.9988943,0.000006792021,0.0001840971,0.0005685161,0.0001857111,0.0001605832],"domain_scores_gemma":[0.9954779,0.0001327662,0.00006442172,0.004279817,0.00002098607,0.00002413711],"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":[0.000003134155,0.00002224193,0.000111994,0.000237233,0.00003809844,0.000004755499,0.00008420239,0.007584331,0.002865457,0.02480966,0.001642173,0.9625967],"study_design_scores_gemma":[0.0001265646,0.00001778575,0.00200954,0.00004212225,0.000004071866,0.0000112576,0.00004971915,0.9546802,0.0002448893,0.04205254,0.0006385626,0.0001227615],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04200337,0.0007185042,0.9524616,0.002222038,0.0001088582,0.0002136266,0.00007991601,0.002171858,0.00002023451],"genre_scores_gemma":[0.6117988,0.0001879402,0.3877741,0.000008271109,0.00001738557,0.00001355071,0.000191226,0.000008165406,4.678164e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624739,"threshold_uncertainty_score":0.9958328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1451047171894062,"score_gpt":0.3128175982545535,"score_spread":0.1677128810651473,"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."}}