{"id":"W2418050709","doi":"10.1109/tcyb.2017.2766189","title":"Learning Stylometric Representations for Authorship Analysis","year":2017,"lang":"en","type":"preprint","venue":"IEEE Transactions on Cybernetics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Zayed University; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Natural language processing; Word2vec; Artificial intelligence; Latent Dirichlet allocation; Representation (politics); Latent semantic analysis; Feature (linguistics); Sentence; Set (abstract data type); Psycholinguistics; Feature engineering; Attributive; Linguistics; Topic model; Deep learning; Politics; Psychology","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"],"consensus_categories":[],"category_scores_codex":[0.00115024,0.0004012507,0.0005822806,0.001677807,0.001115448,0.0009079344,0.001772837,0.0006218755,0.00005716516],"category_scores_gemma":[0.0002126047,0.0004454223,0.0009078209,0.001458585,0.00009356486,0.0002010753,0.00003287573,0.001742128,0.00006829595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001722446,"about_ca_system_score_gemma":0.0002393463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134732,"about_ca_topic_score_gemma":0.00007581941,"domain_scores_codex":[0.9969068,0.000325742,0.0005907725,0.001103242,0.0005636298,0.0005098564],"domain_scores_gemma":[0.9959854,0.0008437944,0.0005783937,0.001906879,0.0004163965,0.0002691409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003134087,0.0002292328,0.0003324609,0.0001141419,0.001457794,0.000008162187,0.002107719,0.9239594,0.00005485932,0.006270422,0.0001887365,0.06524573],"study_design_scores_gemma":[0.0005728898,0.0002391735,0.001840742,0.00008813425,0.001878154,0.000004724519,0.00007445846,0.9660204,0.008290414,0.01682333,0.003191865,0.0009757303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002449703,0.0001116517,0.9918293,0.001064307,0.002270786,0.0006494017,0.000153682,0.0004442057,0.00102694],"genre_scores_gemma":[0.93262,0.000146413,0.05804278,0.00005864047,0.0001156303,0.0002615604,0.0000709891,0.00003579533,0.008648202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9337866,"threshold_uncertainty_score":0.9997997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07844246020336623,"score_gpt":0.3524052087635211,"score_spread":0.2739627485601549,"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."}}