{"id":"W2885704429","doi":"10.5339/qfarc.2018.ictpd879","title":"Annotation Guidelines for Text Analytics in Social Media","year":2018,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Annotation; Modern Standard Arabic; Computer science; Variety (cybernetics); Social media; Arabic; Profiling (computer programming); Analytics; Natural language processing; Linguistics; Artificial intelligence; World Wide Web; Data science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005145615,0.00004558669,0.00006570783,0.000074127,0.00009155747,0.00004402623,0.0002026183,0.00004577839,0.00002547068],"category_scores_gemma":[0.0005331835,0.00003981985,0.00002604304,0.0003354514,0.00002376603,0.0001636824,0.00003931393,0.00003191534,0.00004250081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001884844,"about_ca_system_score_gemma":0.00004249185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000048221,"about_ca_topic_score_gemma":0.00009591268,"domain_scores_codex":[0.9994209,0.00002151267,0.0001897738,0.0001362028,0.00009977441,0.0001318336],"domain_scores_gemma":[0.9993259,0.0001104468,0.00003973593,0.00008423007,0.0004144998,0.00002518296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001133314,0.00002146974,0.00109628,0.000007342565,0.000005074584,7.140661e-7,0.003380435,0.00001980231,0.0004358165,0.8354898,0.04487358,0.1146584],"study_design_scores_gemma":[0.0006336923,0.00005807303,0.008543179,0.000009470907,0.000004244213,0.000001295804,0.0002930782,0.8668371,0.008215494,0.08639339,0.02878623,0.0002247543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004600008,0.000009757961,0.986302,0.007336651,0.0003274892,0.00006912283,0.000002181046,0.00006407373,0.001288692],"genre_scores_gemma":[0.809527,0.00000138454,0.1880104,0.001408182,0.0006595005,0.000006823451,0.000008831329,0.000003195119,0.0003746432],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8668173,"threshold_uncertainty_score":0.1623806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2373113529841914,"score_gpt":0.4173617885935614,"score_spread":0.18005043560937,"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."}}