{"id":"W2963665652","doi":"10.3390/bdcc3030044","title":"Archetype-Based Modeling and Search of Social Media","year":2019,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Compute Canada","keywords":"Archetype; Jargon; Social media; Vocabulary; Computer science; Set (abstract data type); Relevance (law); Information retrieval; Slang; Data science; World Wide Web; Linguistics","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":[0.0004457503,0.00009470876,0.0001928234,0.0001134851,0.00009326612,0.00005543353,0.0004556653,0.00003778518,0.000001504179],"category_scores_gemma":[0.0001124765,0.00009193647,0.00001929,0.0002281852,0.0000771198,0.0002191878,0.001238404,0.0001233023,0.000002440685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005295524,"about_ca_system_score_gemma":0.00004702382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001010152,"about_ca_topic_score_gemma":0.000005215843,"domain_scores_codex":[0.9989619,0.0000704895,0.0001707434,0.0004276227,0.0001973403,0.0001719413],"domain_scores_gemma":[0.9990217,0.0004462374,0.0000674564,0.000267051,0.0001545383,0.00004301352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009054255,0.00002148942,0.002196888,0.00003867818,0.00002197124,0.000002403413,0.0008483481,0.00003873577,0.0008135216,0.00198434,0.00000514109,0.9940194],"study_design_scores_gemma":[0.0003153181,0.00002369304,0.00178461,0.0000793103,0.00001631173,0.000002035172,0.0002357683,0.9949993,0.001405331,0.00099968,0.00001901347,0.000119553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3096317,0.0001264035,0.6898922,0.00004250671,0.0000233626,0.00006312862,0.0000168993,0.00004197695,0.0001618385],"genre_scores_gemma":[0.9687459,0.000009727015,0.03105618,0.00007252993,0.00005513779,5.566594e-7,0.00005155566,0.000005971886,0.000002440594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9949607,"threshold_uncertainty_score":0.374906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1172107362200819,"score_gpt":0.3397729561917595,"score_spread":0.2225622199716776,"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."}}