{"id":"W4408238568","doi":"10.7763/ijcte.2025.v17.1366","title":"Enhancing Tag Recommendation Precision on Stack Overflow Data Warehouse: An Integrated Approach Combining Numeric Attributes, Feature Extraction Techniques, and Multiple Machine Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"International Journal of Computer Theory and Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Stack (abstract data type); Data mining; Data warehouse; Algorithm; Machine learning; Feature (linguistics); Artificial intelligence; Operating system","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":[0.001295256,0.0001609264,0.000184732,0.0003222903,0.0001200379,0.000378611,0.0007574523,0.00006951427,0.000001843817],"category_scores_gemma":[0.0001212442,0.0001449806,0.00002649872,0.0002097143,0.00001650609,0.001333465,0.0003812423,0.0005166891,3.887862e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006397483,"about_ca_system_score_gemma":0.0000306671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009060913,"about_ca_topic_score_gemma":7.482721e-7,"domain_scores_codex":[0.9989128,0.000114237,0.0003320838,0.0003124712,0.0002006115,0.0001278515],"domain_scores_gemma":[0.9988231,0.0004807494,0.0002068205,0.0002491081,0.0001692398,0.00007099898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006171289,0.0001121482,0.00009954975,0.00001489256,0.0001001764,0.00001190754,0.0002246339,0.007670991,0.0007955781,0.00470537,0.0001848525,0.9860182],"study_design_scores_gemma":[0.0004663738,0.0001485617,0.0004079713,0.0002555104,0.00001218143,0.0002438165,0.00004651877,0.9711709,0.001326637,0.0002662466,0.02551764,0.0001376478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005470247,0.0002092768,0.9931527,0.0003138961,0.0006052546,0.00008322959,0.00003351272,0.0001052298,0.0000266798],"genre_scores_gemma":[0.2233536,0.0002828082,0.7755557,0.0001042818,0.0003002325,0.0000041986,0.0003392473,0.00001663242,0.00004328027],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9858806,"threshold_uncertainty_score":0.5912138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01649627597894825,"score_gpt":0.2781303409130938,"score_spread":0.2616340649341455,"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."}}