{"id":"W2970253329","doi":"10.5539/ijel.v9n5p182","title":"Towards a Linguistic Stylometric Model for the Authorship Detection in Cybercrime Investigations","year":2019,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Class (philosophy); Artificial intelligence; Word (group theory); Part of speech; Stylometry; Relation (database); Information retrieval; Linguistics; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001886555,0.0001253885,0.0001814904,0.0005801647,0.00007313871,0.000219785,0.001233712,0.0001038128,0.000006960874],"category_scores_gemma":[0.1519147,0.0001015914,0.0001434177,0.0005443269,0.00003648955,0.0001303576,0.0001169277,0.0004932867,0.00000645314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002200486,"about_ca_system_score_gemma":0.0003702687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001895459,"about_ca_topic_score_gemma":0.00002521389,"domain_scores_codex":[0.9983059,0.00007731481,0.0006540141,0.0001755906,0.0005830578,0.0002040802],"domain_scores_gemma":[0.983209,0.001172292,0.0004343487,0.0002370051,0.01483485,0.0001125326],"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":[0.0001636173,0.000212059,0.004544774,0.00004634831,0.0002243511,0.00002134552,0.01027686,0.1074347,0.0001780439,0.8634599,0.0007070781,0.01273095],"study_design_scores_gemma":[0.0009201963,0.0001125011,0.001340211,0.00007306627,0.00003091367,0.000004768027,0.00009752201,0.8802174,0.001796061,0.07662164,0.03859743,0.0001882561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007504662,0.0002095032,0.9634597,0.0002176665,0.02464505,0.0002282095,0.00001917071,0.00003999608,0.003676088],"genre_scores_gemma":[0.9643407,0.00002228427,0.0316578,0.0002425363,0.003526382,0.000007097687,0.000003499784,0.00001160326,0.0001880893],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956836,"threshold_uncertainty_score":0.855229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04973140992142759,"score_gpt":0.3193286523017836,"score_spread":0.269597242380356,"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."}}