{"id":"W2563852449","doi":"10.3389/fdata.2019.00013","title":"Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries","year":2019,"lang":"en","type":"review","venue":"Frontiers in Big Data","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":728,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Variety (cybernetics); Data science; Social media; Sanity; Core (optical fiber); Big data; Computer science; Internet privacy; Psychology; Public relations; Management science; Sociology; Engineering ethics; Political science; World Wide Web; Engineering; Data mining; Artificial intelligence","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":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":["open_science","research_integrity"],"category_scores_codex":[0.01005909,0.0003875598,0.001827009,0.0002593514,0.001079253,0.0009129522,0.006197559,0.002047345,0.00002720931],"category_scores_gemma":[0.01964075,0.0003375466,0.00009593864,0.0006051174,0.002076388,0.0006821513,0.008672892,0.002304892,0.00003397254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002158548,"about_ca_system_score_gemma":0.001859681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003385123,"about_ca_topic_score_gemma":0.002807108,"domain_scores_codex":[0.9922355,0.004301046,0.0006597872,0.001535715,0.0006624238,0.0006054981],"domain_scores_gemma":[0.9956489,0.000958982,0.0003669053,0.002831991,0.00003983227,0.0001534214],"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":[0.00001023344,0.00002230228,0.00002461338,0.001160107,0.00005170097,0.000008762945,0.0003286337,2.322877e-9,4.907359e-9,0.002006884,0.3590126,0.6373742],"study_design_scores_gemma":[0.0001666103,0.00001861693,0.00001557836,0.0008998677,0.0003523287,0.000004745814,0.0003852834,0.00001532266,8.789684e-9,0.005444213,0.9922838,0.0004136797],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.65134e-7,0.975653,0.007555453,0.001552645,0.00613195,0.0009438035,0.00751781,0.00008500049,0.0005599007],"genre_scores_gemma":[0.000002066962,0.9655547,0.01476033,0.0001972243,0.002537725,0.00002507007,0.01676801,0.00002933188,0.0001255732],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6369605,"threshold_uncertainty_score":0.9999968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6574308753712388,"score_gpt":0.5028642381828976,"score_spread":0.1545666371883412,"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."}}