{"id":"W3106900815","doi":"","title":"To Train or Not to Train? How Training Affects the Diversity of Crowdsourced Data","year":2020,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Memorial University of Newfoundland","funders":"","keywords":"Training (meteorology); Diversity (politics); Crowdsourcing; Computer science; Training set; Data science; Artificial intelligence; World Wide Web; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.01951027,0.0003902099,0.0004834231,0.0004458181,0.001660059,0.002224337,0.001151334,0.001672296,0.002865639],"category_scores_gemma":[0.1375422,0.0003552432,0.0003851228,0.0004771781,0.002772961,0.004001013,0.001758399,0.001708442,0.0007830887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217406,"about_ca_system_score_gemma":0.001551333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006518496,"about_ca_topic_score_gemma":0.008494174,"domain_scores_codex":[0.9854033,0.01021375,0.0004494177,0.001942203,0.001193599,0.0007977618],"domain_scores_gemma":[0.8919631,0.0848501,0.006960292,0.008713447,0.004308084,0.003205049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003018147,0.00306846,0.5264344,0.001165851,0.0005662267,0.0004276403,0.03098569,0.02842862,0.03333173,0.009719686,0.00891581,0.3539377],"study_design_scores_gemma":[0.0007952384,0.003466359,0.6784094,0.001635693,0.0008295766,0.0006841584,0.03721182,0.1204617,0.03983212,0.07542821,0.04074561,0.0005001997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9650148,0.0002887925,0.01706322,0.006069765,0.0001400953,0.0002283433,0.0001653157,0.0001727654,0.01085691],"genre_scores_gemma":[0.9905565,0.0001012871,0.007153429,0.0008757592,0.00002593221,0.0001532361,0.00008627205,0.00004128596,0.00100618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01951027,"threshold_uncertainty_score":0.1031814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08824991019651553,"score_gpt":0.2701563861884323,"score_spread":0.1819064759919168,"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."}}