{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3132461,0.001564939,0.003353101,0.01088561,0.004537066,0.01498977,0.004766791,0.007171352,0.001663295],"category_scores_gemma":[0.3641181,0.001220233,0.002043268,0.01921425,0.03699019,0.02079508,0.01075728,0.009845755,0.0007814316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008820754,"about_ca_system_score_gemma":0.02910606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004546772,"about_ca_topic_score_gemma":0.006339766,"domain_scores_codex":[0.6184732,0.2959705,0.02732054,0.01012605,0.04593354,0.002176036],"domain_scores_gemma":[0.327307,0.6048968,0.02322987,0.01921017,0.02392644,0.0014298],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000940399,0.00005213196,0.003400178,0.03734056,0.0007091673,0.0002382454,0.01371479,0.0007606485,0.0002615588,0.4808566,0.02384672,0.4387253],"study_design_scores_gemma":[0.0000579305,0.0000591573,0.00248338,0.08805381,0.0004062074,0.0007763269,0.01245148,0.000921251,0.0007140063,0.5331717,0.360761,0.0001437486],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00206632,0.7726052,0.03051064,0.1803124,0.004841945,0.0003289419,0.0002533451,0.00006789872,0.009013218],"genre_scores_gemma":[0.0966336,0.7645132,0.05939125,0.06496809,0.01005619,0.002356753,0.0003098009,0.0001744743,0.001596688],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6867539,"threshold_uncertainty_score":0.8468898,"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."}}