{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.02319142,0.0006633495,0.001420017,0.00323451,0.000917465,0.001466142,0.01935172,0.0002243325,0.00005238086],"category_scores_gemma":[0.001357535,0.0004209233,0.0005069477,0.0046734,0.002386113,0.004122646,0.003678572,0.0004827571,0.0000269807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005775,"about_ca_system_score_gemma":0.001012659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001877284,"about_ca_topic_score_gemma":0.001236006,"domain_scores_codex":[0.9854631,0.0001816655,0.003881383,0.002337095,0.007119822,0.001016958],"domain_scores_gemma":[0.984163,0.0007280979,0.005302234,0.0008405672,0.008757576,0.0002084828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002654594,0.000145663,0.01541323,0.0003279044,0.0001417334,4.363859e-7,0.009523423,0.00009021707,0.0000658077,0.9705771,0.001020488,0.002428605],"study_design_scores_gemma":[0.0008517168,0.0006436309,0.01883464,0.003160098,0.00003868625,0.00001771509,0.9668316,0.001429031,0.0001366746,0.004433834,0.003120709,0.0005016407],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.05299052,0.00008922962,0.0001773829,0.03588538,0.002605828,0.001832338,0.002886231,0.0000798939,0.9034532],"genre_scores_gemma":[0.9973583,0.00005577816,0.0007074539,0.0005318781,0.0004039966,0.0001264881,0.000015369,0.00001987492,0.0007808913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9661432,"threshold_uncertainty_score":0.9998243,"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."}}