{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00778106,0.00006875711,0.0002439497,0.0001971255,0.0003795064,0.0007519362,0.001425114,0.00005055229,0.001020205],"category_scores_gemma":[0.001622724,0.00005590063,0.00002415488,0.0001805578,0.0001551428,0.002334075,0.0007454415,0.0001564701,0.0000473598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002952325,"about_ca_system_score_gemma":0.0002378324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007405187,"about_ca_topic_score_gemma":0.000705039,"domain_scores_codex":[0.9983313,0.0007067525,0.0003629586,0.00008875324,0.0003075978,0.0002026253],"domain_scores_gemma":[0.9984491,0.0006811149,0.0003524121,0.0002678866,0.0001452625,0.0001042044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001032951,0.00002446351,0.0001319465,0.00002209836,0.00009834507,0.00006142068,0.1208106,0.000004140831,0.00008980297,0.04638572,0.7851202,0.04714796],"study_design_scores_gemma":[0.000516592,0.00007914054,0.002486311,0.00002784269,0.00003436911,0.00009091612,0.0927248,0.0000880439,0.00004070457,0.005240121,0.8985665,0.0001046563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.3881285,0.001234724,0.02048494,0.02820524,0.007135948,0.001432849,0.0006048884,0.0001763782,0.5525965],"genre_scores_gemma":[0.3039359,0.009918678,0.4442974,0.03131739,0.005752069,0.000008179623,0.0005691686,0.0001492136,0.204052],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4238125,"threshold_uncertainty_score":0.999893,"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."}}