{"id":"W3123386990","doi":"10.18280/isi.250606","title":"Assessment of Twitter Data Clusters with Cosine-Based Validation Metrics Using Hybrid Topic Models","year":2020,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Computer science; Cosine similarity; Set (abstract data type); Data mining; Metric (unit); Trigonometric functions; Data set; Euclidean distance; Cluster (spacecraft); Artificial intelligence; Information retrieval; Pattern recognition (psychology); Mathematics; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002126212,0.0001360421,0.0002329431,0.0001651647,0.00008693727,0.0001265047,0.0002788892,0.00002083221,0.00004628483],"category_scores_gemma":[0.000009630941,0.0001236233,0.00004791325,0.0005359174,0.00004670648,0.0018382,0.0001179309,0.00008882386,0.000001563939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009080174,"about_ca_system_score_gemma":0.0001204012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001558576,"about_ca_topic_score_gemma":7.213977e-7,"domain_scores_codex":[0.9989181,0.00004175206,0.0004793446,0.000134814,0.0002824457,0.0001435969],"domain_scores_gemma":[0.9988578,0.00004108974,0.0004465175,0.0003800494,0.0002220113,0.00005251767],"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":[0.0000927561,0.0001410125,0.1031748,0.0007477269,0.0005403232,0.000001549269,0.00240986,0.8113562,0.000821117,0.006652216,0.002272041,0.07179044],"study_design_scores_gemma":[0.0003176659,0.00005661491,0.0006871777,0.00008138179,0.00008606062,5.041117e-7,0.0002149845,0.9946094,0.002753461,0.000798534,0.0002516739,0.000142582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2390536,0.000005000541,0.7586663,0.00003915159,0.00001444819,0.0002076482,0.00004988499,0.00004516242,0.001918845],"genre_scores_gemma":[0.956761,6.381243e-7,0.04173765,0.0001356939,0.00006064922,0.00001122614,0.001282104,0.00000937839,0.000001661425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7177075,"threshold_uncertainty_score":0.5041213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06814756327762954,"score_gpt":0.2970766632107695,"score_spread":0.22892909993314,"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."}}