{"id":"W3158254122","doi":"10.3389/frai.2021.648543","title":"Considering Performance in the Automated and Manual Coding of Sociolinguistic Variables: Lessons From Variable (ING)","year":2021,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Coding (social sciences); Computer science; Natural language processing; Artificial intelligence; Speech recognition; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.1478833,0.001887845,0.001213423,0.003987889,0.002762308,0.00726857,0.003809894,0.002274853,0.001542599],"category_scores_gemma":[0.4064315,0.0009591444,0.0009147406,0.003422862,0.008154775,0.009509402,0.005274119,0.003007647,0.001512001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003027757,"about_ca_system_score_gemma":0.004771817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01220113,"about_ca_topic_score_gemma":0.01770715,"domain_scores_codex":[0.7867355,0.1576761,0.009528255,0.02023956,0.02416857,0.001651889],"domain_scores_gemma":[0.3986427,0.4133216,0.04093823,0.07393335,0.07060103,0.002563102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005850256,0.0002976267,0.1626206,0.001531222,0.0007974693,0.0002334048,0.06564784,0.01622422,0.01529126,0.03339669,0.01009579,0.6932788],"study_design_scores_gemma":[0.00019518,0.001860478,0.3318758,0.003000061,0.0004123096,0.001523835,0.05143034,0.1858114,0.08022192,0.2527262,0.08910325,0.001839265],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2356629,0.002323935,0.740943,0.00530153,0.000719464,0.0005708124,0.0007887315,0.001456601,0.01223299],"genre_scores_gemma":[0.6362496,0.0005763039,0.358651,0.001065908,0.0002507787,0.0005870902,0.0005689898,0.0007644133,0.001286006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1478833,"threshold_uncertainty_score":0.7820909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06119933609840694,"score_gpt":0.3479488632275913,"score_spread":0.2867495271291843,"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."}}