{"id":"W4229069564","doi":"10.2196/35266","title":"Enhancing COVID-19 Epidemic Forecasting Accuracy by Combining Real-time and Historical Data From Multiple Internet-Based Sources: Analysis of Social Media Data, Online News Articles, and Search Queries","year":2022,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"City University of Hong Kong","keywords":"The Internet; Computer science; Social media; Data science; Big data; Data mining; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.004572699,0.001233958,0.0008755161,0.01151574,0.000419944,0.001870762,0.000653534,0.001064088,0.0005942704],"category_scores_gemma":[0.01429167,0.0003198305,0.001719283,0.006184283,0.0003702751,0.002845937,0.001075783,0.001172659,0.0004411251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007668392,"about_ca_system_score_gemma":0.0007795165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01667544,"about_ca_topic_score_gemma":0.01423851,"domain_scores_codex":[0.9982413,0.0005673715,0.0002641495,0.0003470875,0.0003805473,0.0001995105],"domain_scores_gemma":[0.9860487,0.01016305,0.001443169,0.0007176971,0.001316175,0.0003112556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000555689,0.0007207824,0.8344002,0.0006496836,0.0009410723,0.0007855192,0.0005248657,0.0526873,0.001881803,0.0008805507,0.006599288,0.09937312],"study_design_scores_gemma":[0.00005152015,0.0002133692,0.3671526,0.0001873637,0.0004871821,0.0004245361,0.001250101,0.6209393,0.001971925,0.002120754,0.005100055,0.0001012448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726333,0.003256686,0.008829113,0.001657204,0.00017602,0.0001351202,0.0107552,0.0003067049,0.002250592],"genre_scores_gemma":[0.9691622,0.001065731,0.01068286,0.0001290196,0.0002477777,0.00007158696,0.01813217,0.00002764093,0.0004809865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01667544,"threshold_uncertainty_score":0.03315675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1603240612307615,"score_gpt":0.369769992526947,"score_spread":0.2094459312961855,"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."}}