{"id":"W1988047293","doi":"10.1007/s10115-013-0617-y","title":"Analyzing topics and authors in chat logs for crime investigation","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Exploit; Latent Dirichlet allocation; Online chat; Process (computing); The Internet; Order (exchange); Volume (thermodynamics); Channel (broadcasting); Topic model; Data science; World Wide Web; Information retrieval; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.0003211792,0.00006092666,0.00009823649,0.0001581805,0.00006161073,0.0002883639,0.00009399516,0.00005785878,5.486922e-7],"category_scores_gemma":[0.00004028002,0.00005456853,0.00001034367,0.0001219828,0.00001186728,0.003366254,0.00005402809,0.00004471911,0.00001750556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002294549,"about_ca_system_score_gemma":0.00002252171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007558599,"about_ca_topic_score_gemma":0.000004022404,"domain_scores_codex":[0.9994371,0.00002480692,0.0002930866,0.0000885246,0.00005024944,0.0001062581],"domain_scores_gemma":[0.9996111,0.00003247681,0.00007583302,0.0001179637,0.0001055429,0.0000571171],"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":[0.000002097954,0.00001152739,0.02018773,0.0009843673,0.00001396367,1.601964e-7,0.04256824,0.0003161691,0.0002247831,0.5953673,0.002050033,0.3382736],"study_design_scores_gemma":[0.0002730715,0.00002029261,0.008983702,0.00006382536,0.00000166773,0.000004216295,0.0003341092,0.9718997,0.0001011558,0.001223511,0.01699638,0.0000983695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1806931,0.001004975,0.8112191,0.0006030799,0.0006956006,0.0007968963,0.000001260305,0.00008133356,0.004904574],"genre_scores_gemma":[0.9960768,0.0000235415,0.003438001,0.00007023927,0.0000751913,0.00007781833,0.000005507286,0.000001927065,0.0002310168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9715835,"threshold_uncertainty_score":0.27807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02670907494937454,"score_gpt":0.2508178429459265,"score_spread":0.224108767996552,"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."}}