{"id":"W2954574984","doi":"10.1109/msr.2019.00052","title":"What do Developers Know About Machine Learning: A Study of ML Discussions on StackOverflow","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Machine learning; Artificial intelligence; Topic model; Software; Focus (optics); Data science","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":[],"category_scores_codex":[0.006233374,0.0003029515,0.0003703748,0.002649787,0.003829363,0.003631717,0.0007489638,0.001840631,0.003254607],"category_scores_gemma":[0.05510268,0.0004243058,0.0002085716,0.001956491,0.001744448,0.008890771,0.002817085,0.002715631,0.00112859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002038168,"about_ca_system_score_gemma":0.001076668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00741179,"about_ca_topic_score_gemma":0.01060004,"domain_scores_codex":[0.9959468,0.00243725,0.000211071,0.0003668846,0.0006050659,0.0004328927],"domain_scores_gemma":[0.9246711,0.05312979,0.01084695,0.001682051,0.005239497,0.004430582],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002646013,0.0005311273,0.190105,0.0001796574,0.00002511571,0.0006370076,0.7622221,0.0001290135,0.002098146,0.00147965,0.006326404,0.03600216],"study_design_scores_gemma":[0.00005966035,0.0004763553,0.2861346,0.0002755965,0.00002862491,0.0004419704,0.6525593,0.002327714,0.0012684,0.001595569,0.05471303,0.0001191492],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931977,0.0001931521,0.0004512276,0.001958634,0.00002043411,0.00002412568,0.0001311579,0.00004033019,0.003983115],"genre_scores_gemma":[0.9954956,0.0002490926,0.0004006887,0.0008756818,0.00006546386,0.00005330475,0.0003066871,0.00007230858,0.002481161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9937666,"threshold_uncertainty_score":0.03296566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397952711583728,"score_gpt":0.2750782205586064,"score_spread":0.2610986934427691,"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."}}