{"id":"W6944725459","doi":"10.21227/zece-e657","title":"Stack Overflow Dataset for User Engagement, Technology and Emotion Analysis","year":2025,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Stack (abstract data type); Key (lock); Reputation; User engagement; Big data; Data source; Emotion classification","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001634294,0.000842011,0.001387368,0.005157002,0.0003407596,0.0002311134,0.00173849,0.000914634,0.0005024019],"category_scores_gemma":[0.0006469354,0.0008955342,0.0002172737,0.003971642,0.0002824354,0.0005754603,0.0009929017,0.0009600959,0.0003726034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002205648,"about_ca_system_score_gemma":0.0003535355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004333401,"about_ca_topic_score_gemma":0.001509881,"domain_scores_codex":[0.9954125,0.0001662871,0.0009943041,0.002017651,0.0006036097,0.0008056649],"domain_scores_gemma":[0.992973,0.000222987,0.0008166874,0.0056105,0.0002074611,0.0001693193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009192211,0.0002217655,0.0004844039,0.0004242721,0.00479868,0.00006371388,0.000002764034,0.00002236395,0.00005870789,0.00002074634,0.9936611,0.000149562],"study_design_scores_gemma":[0.0009164216,0.00008428259,0.0002104278,0.00006810031,0.01254594,0.000009642648,0.00003072392,0.00009693279,0.000120571,0.0000500411,0.9851117,0.0007552551],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001351613,0.000129796,0.001479113,0.00008654143,0.0006527203,0.00150818,0.9958321,0.0001666746,0.000009748763],"genre_scores_gemma":[0.00001793411,0.0003474322,0.001157846,0.0002748577,0.000215333,0.0003543757,0.997114,0.0000642574,0.0004539551],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.008549435,"threshold_uncertainty_score":0.9993495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03213331979825961,"score_gpt":0.3372897989300214,"score_spread":0.3051564791317617,"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."}}