{"id":"W3176912690","doi":"10.7910/dvn/g98bqg","title":"CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing","year":2021,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Social media; Computer science; Data science; Political science; Business; World Wide Web; Marketing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004088474,0.003212784,0.001043145,0.007792487,0.001958095,0.002798409,0.00379349,0.002902142,0.01378538],"category_scores_gemma":[0.01474953,0.0006109026,0.001859211,0.007923899,0.00115245,0.005426622,0.004931191,0.002721902,0.01933268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002437136,"about_ca_system_score_gemma":0.002606651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0344377,"about_ca_topic_score_gemma":0.03872058,"domain_scores_codex":[0.9950021,0.001488171,0.0006833929,0.001051362,0.001274724,0.0005002127],"domain_scores_gemma":[0.9942155,0.001418023,0.000388687,0.001774145,0.001518089,0.0006854743],"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":[0.0004486307,0.0003631269,0.005132089,0.001175485,0.0001522834,0.0001486793,0.0002986727,0.005167336,0.001231391,0.002002465,0.9498461,0.03403367],"study_design_scores_gemma":[0.000806372,0.000412118,0.03863436,0.0007483474,0.000172268,0.0005201034,0.003806265,0.06397187,0.007940613,0.007792918,0.8749357,0.0002591248],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02026275,0.001386328,0.004658183,0.002665506,0.001005363,0.0007617627,0.9433659,0.01482529,0.01106885],"genre_scores_gemma":[0.0103781,0.000214805,0.004975448,0.0002641505,0.00008214229,0.0003332118,0.9820257,0.000337914,0.001388493],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0344377,"threshold_uncertainty_score":0.06847447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03225268753770763,"score_gpt":0.3070516844936019,"score_spread":0.2747989969558943,"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."}}