{"id":"W3205467272","doi":"10.1145/3534678.3539077","title":"TAG: Toward Accurate Social Media Content Tagging with a Concept Graph","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Computer science; Social media; Conceptualization; Graph; User-generated content; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Theoretical computer 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":[],"consensus_categories":[],"category_scores_codex":[0.001386906,0.001510585,0.0006371842,0.009160057,0.0009066276,0.001462023,0.002077584,0.002080533,0.002181522],"category_scores_gemma":[0.007495434,0.0004284091,0.00138092,0.005629731,0.0007951894,0.005537635,0.002186909,0.001670887,0.002667674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001540987,"about_ca_system_score_gemma":0.001728856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277457,"about_ca_topic_score_gemma":0.02277476,"domain_scores_codex":[0.9984961,0.0003316634,0.0001051894,0.0006089804,0.0003602318,0.00009790636],"domain_scores_gemma":[0.9973605,0.00123777,0.0003193212,0.0004866293,0.0004888423,0.0001068275],"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":[0.0008368722,0.0009564028,0.02806393,0.002227064,0.0004727228,0.001028002,0.00182597,0.04409645,0.03215746,0.05827442,0.1468467,0.6832141],"study_design_scores_gemma":[0.0001613523,0.0002370206,0.00931131,0.0002250732,0.0002021757,0.0008449462,0.001331523,0.7323746,0.0248539,0.1015728,0.1287743,0.0001109047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1089098,0.002559778,0.7954513,0.001408863,0.0004754209,0.0009778802,0.05152072,0.0299664,0.008729776],"genre_scores_gemma":[0.2205997,0.0006717053,0.6836305,0.0007449963,0.000122584,0.0006615438,0.08854976,0.0009531633,0.004066143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01277457,"threshold_uncertainty_score":0.0254004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.15618565245343,"score_gpt":0.2986985138738367,"score_spread":0.1425128614204067,"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."}}