{"id":"W2782105765","doi":"10.24251/hicss.2018.096","title":"Data Quality Challenges in Twitter Content Analysis for Informing Policy Making in Health Care","year":2018,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social media; Microblogging; Computer science; Variety (cybernetics); Process (computing); Profiling (computer programming); Reliability (semiconductor); Content analysis; Set (abstract data type); Data science; Quality (philosophy); World Wide Web; Sociology; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1829368,0.0009346344,0.002022203,0.009177966,0.004691093,0.02216363,0.004528331,0.005817742,0.001795017],"category_scores_gemma":[0.46734,0.001499052,0.0009843137,0.01225248,0.007729889,0.01631177,0.007405712,0.004538876,0.0009088165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00836355,"about_ca_system_score_gemma":0.01064882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01825634,"about_ca_topic_score_gemma":0.01441672,"domain_scores_codex":[0.7993025,0.1461396,0.01481733,0.006794699,0.03096036,0.001985459],"domain_scores_gemma":[0.3409472,0.5690483,0.02378712,0.02258904,0.04115628,0.002472068],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001296827,0.0008309381,0.1222569,0.008206322,0.0008440677,0.001358008,0.03828197,0.04582983,0.008663277,0.2123319,0.06216735,0.4979326],"study_design_scores_gemma":[0.0003265499,0.0004187881,0.04303335,0.005310865,0.000417459,0.001396129,0.05595766,0.2291902,0.01304743,0.4790784,0.1712377,0.0005855882],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1499852,0.01883277,0.4849536,0.310415,0.00157358,0.003269054,0.006325753,0.001103259,0.02354181],"genre_scores_gemma":[0.6280223,0.005885376,0.3490618,0.008168582,0.00220313,0.001953191,0.00245438,0.0004639482,0.00178727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8170632,"threshold_uncertainty_score":0.9674739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4859159744974482,"score_gpt":0.4817864261405992,"score_spread":0.004129548356848978,"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."}}