{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006457295,0.0002716536,0.000372313,0.0001258945,0.0006498155,0.0004903885,0.004764075,0.00004714113,0.00001442802],"category_scores_gemma":[0.0004458938,0.0001981478,0.00005956535,0.0004715188,0.0002387282,0.001967719,0.006575915,0.0003969491,0.000001112335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000431165,"about_ca_system_score_gemma":0.0002412932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001444957,"about_ca_topic_score_gemma":0.000007757862,"domain_scores_codex":[0.9978117,0.00004024619,0.000378917,0.000860272,0.000504477,0.000404391],"domain_scores_gemma":[0.9983042,0.0002663918,0.0004173691,0.0007128034,0.0002089252,0.00009026057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003962145,0.0003861762,0.006228455,0.0003108268,0.0002259345,0.00001057646,0.09821959,0.00005983399,0.007021954,0.790668,0.00307507,0.09339735],"study_design_scores_gemma":[0.01831416,0.003457018,0.02197512,0.004580704,0.0009587104,0.000490806,0.3571299,0.4497167,0.03684187,0.08788138,0.0108498,0.007803855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733376,0.0005311041,0.01405586,0.004667535,0.0009312686,0.0005749867,0.0003274163,0.0001680156,0.005406218],"genre_scores_gemma":[0.9956607,0.00001947104,0.003744851,0.0002317206,0.0001092601,0.00004701818,0.00001994422,0.00001554005,0.0001514894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7027866,"threshold_uncertainty_score":0.8852916,"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."}}