{"id":"W3165669050","doi":"10.1007/s11135-021-01164-0","title":"Algorithmic thinking in the public interest: navigating technical, legal, and ethical hurdles to web scraping in the social sciences","year":2021,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Winnipeg; Carleton University; University of Toronto","funders":"","keywords":"Context (archaeology); Openness to experience; The Internet; Data sharing; Social media; Computer science; Principle of legality; World Wide Web; Data science; Internet privacy; Knowledge management; Public relations; Engineering ethics; Political science; Engineering; Psychology; Law","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","sts"],"consensus_categories":[],"category_scores_codex":[0.02932939,0.00009678854,0.0002256535,0.00008486362,0.002071254,0.001032303,0.0006901355,0.0001401892,0.00002165442],"category_scores_gemma":[0.004677947,0.00006630199,0.00009617786,0.002277889,0.0007891106,0.0002344408,0.0001949291,0.0009413156,0.000003911037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006220794,"about_ca_system_score_gemma":0.0004073613,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005149908,"about_ca_topic_score_gemma":0.1129986,"domain_scores_codex":[0.9919869,0.006035917,0.0004312891,0.0003518078,0.0008730531,0.0003210708],"domain_scores_gemma":[0.9963589,0.003250593,0.0001100502,0.0001322432,0.000110254,0.00003798389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002446206,0.00007148054,0.01381082,0.00001180822,0.000005825359,0.00001198926,0.02662207,0.000007560797,0.0002427275,0.9467217,0.0000997335,0.01239179],"study_design_scores_gemma":[0.0004890515,0.00008299443,0.3293266,0.000317921,0.00003806274,0.00002109642,0.2757947,0.002629536,0.00004096744,0.3664366,0.02416955,0.0006527834],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8201777,0.0001723295,0.002268042,0.1762933,0.00007313512,0.0001336691,0.000002291511,0.00002519236,0.0008543915],"genre_scores_gemma":[0.9880632,0.00002824416,0.006229956,0.005477095,0.0001774037,0.00001374054,0.000002451803,0.000002939193,0.000004951105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5802851,"threshold_uncertainty_score":0.9995096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.279075911413793,"score_gpt":0.5367740553267564,"score_spread":0.2576981439129634,"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."}}