{"id":"W2741544939","doi":"10.1145/3077136.3080667","title":"Finally, a Downloadable Test Collection of Tweets","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Microblogging; World Wide Web; The Internet; Scalability; Download; Social media; Data collection; Information retrieval; Data science; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003558211,0.001467183,0.001126933,0.004478552,0.002700376,0.002471303,0.001800446,0.001626466,0.00885404],"category_scores_gemma":[0.02117902,0.000623225,0.001234884,0.006123149,0.001310895,0.003583356,0.002731928,0.002706838,0.01111225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307196,"about_ca_system_score_gemma":0.001816035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00928417,"about_ca_topic_score_gemma":0.01914371,"domain_scores_codex":[0.9934088,0.001454473,0.0008355099,0.001122478,0.002538787,0.000640083],"domain_scores_gemma":[0.9749566,0.005113619,0.001238314,0.009474928,0.007942082,0.00127437],"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":[0.002767317,0.002237702,0.03995914,0.002717437,0.00047781,0.001638152,0.002574403,0.005119164,0.02424385,0.003953819,0.790215,0.1240963],"study_design_scores_gemma":[0.0005867591,0.0008978808,0.1231551,0.0003731747,0.000292973,0.001969284,0.003148213,0.03196763,0.06284064,0.004256713,0.7701888,0.0003228212],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.3072153,0.001403745,0.0268721,0.002881962,0.002628552,0.003931649,0.5883589,0.03311367,0.03359417],"genre_scores_gemma":[0.2229802,0.0003932168,0.04679303,0.0007426832,0.0005794963,0.00369759,0.7065464,0.003377535,0.01488998],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.00928417,"threshold_uncertainty_score":0.02961969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0305441985586857,"score_gpt":0.260896675642129,"score_spread":0.2303524770834433,"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."}}