{"id":"W2947784394","doi":"10.25300/misq/2019/14439","title":"Expecting the Unexpected: Effects of Data Collection Design Choices on the Quality of Crowdsourced User-Generated Content1","year":2019,"lang":"en","type":"article","venue":"MIS Quarterly","topic":"Open Source Software Innovations","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; HEC Montréal","funders":"","keywords":"Quality (philosophy); Crowdsourcing; Computer science; User-generated content; Data collection; Data quality; Content (measure theory); User needs; Data science; World Wide Web; Knowledge management; Business; Internet privacy; Marketing; Social media; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.001556961,0.0001629485,0.0002799564,0.0001018444,0.0002435721,0.0001578984,0.002131834,0.00006658428,0.0000194444],"category_scores_gemma":[0.0004429034,0.0001005695,0.00006158234,0.001372636,0.0000861703,0.0004364552,0.00009810814,0.0001935881,0.00002498168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003696527,"about_ca_system_score_gemma":0.00008359609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009986954,"about_ca_topic_score_gemma":0.00006318298,"domain_scores_codex":[0.9973895,0.000926912,0.0005615351,0.0004348423,0.0004719061,0.0002152964],"domain_scores_gemma":[0.9936255,0.003361294,0.0005698183,0.002081274,0.000333579,0.00002856333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002064724,0.0007371094,0.01056794,0.0002283944,0.0005439319,0.000003785424,0.06896624,0.0006991258,0.8606588,0.02564811,0.009842549,0.02189752],"study_design_scores_gemma":[0.006482013,0.006709348,0.1294976,0.0007964061,0.0001310645,0.00002106424,0.02369599,0.1398512,0.6869867,0.001637626,0.002666546,0.001524429],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7935448,0.00004233989,0.2043715,0.0006729089,0.0002969134,0.0007981847,0.000006000767,0.00008897164,0.0001784317],"genre_scores_gemma":[0.9949592,5.149226e-7,0.004433138,0.0001811134,0.0000375015,0.0000364012,0.000008309925,0.00001298008,0.0003307853],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2014145,"threshold_uncertainty_score":0.4101104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08067820091748466,"score_gpt":0.3121066432477392,"score_spread":0.2314284423302546,"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."}}