{"id":"W4382727197","doi":"10.5334/johd.109","title":"A Mixed Method Twitter Methodology and Anonymous Corpus","year":2023,"lang":"en","type":"article","venue":"Journal of Open Humanities Data","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Vetting; Anonymity; Computer science; Field (mathematics); Work (physics); Process (computing); World Wide Web; Simple (philosophy); Data science; Internet privacy; Information retrieval; Computer security; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.009382276,0.0008598697,0.0006681507,0.00405641,0.003597868,0.00268319,0.002333709,0.00277027,0.03182924],"category_scores_gemma":[0.02602014,0.0005943737,0.000656559,0.004650998,0.001837903,0.001919795,0.004211611,0.001885595,0.01651814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001753022,"about_ca_system_score_gemma":0.00344717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007475318,"about_ca_topic_score_gemma":0.01883431,"domain_scores_codex":[0.9919943,0.003731006,0.0007205065,0.001461365,0.001625316,0.0004675746],"domain_scores_gemma":[0.977466,0.01041824,0.001808046,0.004914744,0.004779711,0.0006132862],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001463053,0.0022396,0.03287637,0.005064581,0.0001964193,0.002463165,0.01819644,0.00492753,0.008354375,0.0503372,0.7113634,0.1625179],"study_design_scores_gemma":[0.0003137216,0.0003224825,0.02684705,0.0007979864,0.00008045335,0.0006648229,0.008547773,0.006547071,0.004497183,0.01388894,0.9373196,0.0001728383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1936145,0.00187117,0.09383463,0.005041266,0.002369886,0.02948325,0.5929961,0.003594638,0.07719461],"genre_scores_gemma":[0.1904972,0.0005839791,0.1716594,0.003511851,0.0009679557,0.08086894,0.4976045,0.002099773,0.05220636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906178,"threshold_uncertainty_score":0.1064794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7209269913846231,"score_gpt":0.5227081836891851,"score_spread":0.198218807695438,"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."}}