{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003952087,0.0008324887,0.0008346308,0.009387343,0.0008470814,0.00360374,0.001455398,0.001426545,0.002136997],"category_scores_gemma":[0.01551206,0.0006464703,0.001076145,0.004197561,0.001540172,0.003740838,0.001637028,0.001100251,0.001025391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002019965,"about_ca_system_score_gemma":0.001328568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006379739,"about_ca_topic_score_gemma":0.00464942,"domain_scores_codex":[0.9980223,0.000916793,0.0001388283,0.0003931505,0.000418416,0.0001104276],"domain_scores_gemma":[0.9938679,0.003676007,0.000819343,0.0005571115,0.0009232401,0.0001564253],"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":[0.000267752,0.0007026985,0.1021787,0.0004256529,0.0003668899,0.0005086403,0.003490598,0.4536014,0.00677537,0.1258678,0.00489299,0.3009215],"study_design_scores_gemma":[0.000006252755,0.00002180741,0.006703051,0.00003240592,0.00001413387,0.00006533827,0.0001888885,0.9683484,0.0003256022,0.02303006,0.001240717,0.00002321112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1398755,0.0003728184,0.8505725,0.0009088983,0.00007928327,0.0003720111,0.0006965689,0.0008570133,0.006265262],"genre_scores_gemma":[0.8085942,0.0003884569,0.1870274,0.00008258611,0.0001558022,0.0004692498,0.0007338579,0.0001012056,0.002447313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009387343,"threshold_uncertainty_score":0.02090091,"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."}}