{"id":"W4312568851","doi":"10.1609/icwsm.v11i1.14934","title":"A Longitudinal Study of Topic Classification on Twitter","year":2017,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Classifier (UML); Kaleidoscope; Artificial intelligence; Ranging; Entertainment; Machine learning; Feature (linguistics); Natural language processing; Data science; Information retrieval","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":[0.003660102,0.0002641011,0.0004504982,0.001421047,0.001392409,0.001783603,0.0004989638,0.000864441,0.002923603],"category_scores_gemma":[0.02159072,0.0002780198,0.000321523,0.001423551,0.0005170371,0.003025872,0.001231157,0.001597881,0.001792504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006402511,"about_ca_system_score_gemma":0.0004040632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00855931,"about_ca_topic_score_gemma":0.01083476,"domain_scores_codex":[0.9986314,0.0006080644,0.00007594143,0.0002835907,0.0002338621,0.0001670919],"domain_scores_gemma":[0.9855503,0.005864947,0.002673256,0.001665031,0.002942414,0.001303911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000342708,0.0006239983,0.9413908,0.00006156517,0.0001132274,0.0002426057,0.007946673,0.0006467995,0.001650507,0.001490266,0.01225027,0.03324053],"study_design_scores_gemma":[0.00002579321,0.0004712072,0.947255,0.00008375885,0.00008131591,0.0003749836,0.009150423,0.01724722,0.001508726,0.001985166,0.02173846,0.00007808018],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912986,0.0004136528,0.001876282,0.001505232,0.0001001504,0.00004874093,0.00239114,0.00006120564,0.00230505],"genre_scores_gemma":[0.9928077,0.0001747959,0.0009064616,0.0002399449,0.0001324447,0.00007531892,0.003385511,0.00004445847,0.002233349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00855931,"threshold_uncertainty_score":0.01935667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2153179481366862,"score_gpt":0.410507392061086,"score_spread":0.1951894439243998,"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."}}