{"id":"W2530745782","doi":"10.4018/ijban.2017010101","title":"Exploring Insurance and Natural Disaster Tweets Using Text Analytics","year":2016,"lang":"en","type":"article","venue":"International Journal of Business Analytics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Natural disaster; Insurance fraud; Analytics; Business; Flood myth; Flood insurance; Sentiment analysis; Data science; Computer science; Actuarial science; Geography; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003055478,0.0001448384,0.0002639153,0.0005064696,0.00005728043,0.0002791706,0.0007627059,0.00002847483,0.00001397574],"category_scores_gemma":[0.0001576938,0.00009549982,0.0001275948,0.0004665096,0.0000630051,0.002055475,0.0002333139,0.0001007754,0.000003964563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009476665,"about_ca_system_score_gemma":0.00006929209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001113628,"about_ca_topic_score_gemma":0.000003255479,"domain_scores_codex":[0.9983251,0.00003044187,0.0005778078,0.0001915401,0.0007028325,0.0001722558],"domain_scores_gemma":[0.9977748,0.0001402857,0.0005474636,0.0001811704,0.001269376,0.00008693427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001768353,0.0003567847,0.4748374,0.00004171807,0.002605426,0.000708807,0.001627602,0.01275642,0.02057827,0.01415224,0.0003179524,0.4718406],"study_design_scores_gemma":[0.003577398,0.00009409192,0.6356601,0.0015789,0.0002335616,0.0009713247,0.0003758313,0.3448702,0.003408226,0.002037811,0.006280091,0.0009124798],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6484032,0.0002407477,0.3480942,0.001731283,0.001451443,0.00001702485,0.000002274608,0.000008827329,0.00005093268],"genre_scores_gemma":[0.9897531,0.0005356297,0.00898627,0.0001263141,0.0004763842,3.098071e-7,5.843975e-7,0.000009048458,0.0001123767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4709281,"threshold_uncertainty_score":0.3894369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09667198861335495,"score_gpt":0.296674369333476,"score_spread":0.2000023807201211,"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."}}