{"id":"W2759341995","doi":"10.17705/1cais.04114","title":"Using Mechanical Turk Data in IS Research: Risks, Rewards, and Recommendations","year":2017,"lang":"en","type":"article","venue":"Communications of the Association for Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Set (abstract data type); Data science; Computer science; Cognition; Data set; Psychology; Work (physics); Data collection; Applied psychology; Artificial intelligence; Sociology; 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":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.006750606,0.00007185116,0.000163483,0.0001770307,0.001707736,0.0008388332,0.005856952,0.0001037002,2.09834e-7],"category_scores_gemma":[0.004193438,0.00006364521,0.00003964557,0.0002655741,0.00008056925,0.002480841,0.003875882,0.0002417277,0.000004471363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002250761,"about_ca_system_score_gemma":0.0001193539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001087378,"about_ca_topic_score_gemma":0.0001153662,"domain_scores_codex":[0.9983031,0.0004035416,0.000599198,0.0001365325,0.0003770856,0.0001805324],"domain_scores_gemma":[0.990216,0.0007591542,0.001094089,0.007245011,0.0006510322,0.00003476583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001329608,0.0001354717,0.02808245,0.0002102739,0.0001447499,4.436967e-8,0.01104076,0.0007163732,0.0003937402,0.9082565,0.02580509,0.02520125],"study_design_scores_gemma":[0.0007905485,0.00001883793,0.01146709,0.000399774,0.00002206312,0.000005285373,0.001647478,0.7254513,0.0003002424,0.00366691,0.2560452,0.0001853196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08846754,0.004239565,0.4357553,0.3149699,0.01184973,0.01863945,0.004153443,0.0008293055,0.1210958],"genre_scores_gemma":[0.9838489,0.0001115007,0.0157708,0.00006128855,0.00002072204,0.00003448774,0.00004305417,0.000004492213,0.0001046934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9045896,"threshold_uncertainty_score":0.9995919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4302846417830177,"score_gpt":0.460380283125942,"score_spread":0.03009564134292425,"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."}}