{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004757621,0.00006824866,0.0001451936,0.00006705111,0.00047638,0.0001170091,0.0005820067,0.00004474982,0.00007246197],"category_scores_gemma":[0.0006888354,0.00005031616,0.00006107299,0.00005131897,0.0002797889,0.0001169008,0.00009043887,0.0001032941,0.000002024325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003000867,"about_ca_system_score_gemma":0.00006209196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001811284,"about_ca_topic_score_gemma":0.0003858127,"domain_scores_codex":[0.9989242,0.00002302096,0.0001847564,0.0001557578,0.0006324478,0.00007979423],"domain_scores_gemma":[0.9988767,0.0001583721,0.0003793732,0.00005435553,0.0005044505,0.00002678199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008249809,0.0003464827,0.2272508,0.0000101077,0.00009298375,2.196356e-7,0.031331,3.55938e-7,0.001085947,0.7158696,0.0002984339,0.02363156],"study_design_scores_gemma":[0.0004384089,0.00007535846,0.943369,0.00004736446,0.00003578152,1.372656e-7,0.01388817,0.0002664413,0.0001985747,0.04072173,0.0008774176,0.00008165962],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9446809,0.000002109637,0.000003418119,0.009090893,0.0003447748,0.0001066709,0.000003378585,0.000006129494,0.04576168],"genre_scores_gemma":[0.9989232,0.00001489537,0.00005997388,0.00005510095,0.0003196116,0.00001005867,6.567736e-7,0.000002800153,0.0006137235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7161182,"threshold_uncertainty_score":0.3663978,"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."}}