{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01094687,0.001181557,0.001177282,0.005867959,0.00115028,0.002689706,0.001232403,0.001024474,0.0006259686],"category_scores_gemma":[0.04007694,0.0002587839,0.001012038,0.004013759,0.0008863376,0.00321615,0.001983366,0.0008757218,0.0003949623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001272084,"about_ca_system_score_gemma":0.001397511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004554488,"about_ca_topic_score_gemma":0.002927362,"domain_scores_codex":[0.9932652,0.00249746,0.0008556031,0.001135601,0.001953603,0.0002926286],"domain_scores_gemma":[0.9817934,0.008323837,0.002215239,0.001959613,0.005279096,0.0004289307],"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":[0.002501871,0.0008929756,0.2199632,0.00124465,0.0008193234,0.0004002388,0.002162976,0.3509093,0.01785428,0.01893673,0.007899093,0.3764154],"study_design_scores_gemma":[0.00003487296,0.0002255372,0.01839539,0.00005097158,0.00006488705,0.0001397496,0.0004997691,0.9689013,0.007164494,0.003282549,0.001190927,0.00004964299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5859593,0.001251949,0.4044053,0.000423347,0.0001537177,0.0004573587,0.001985679,0.001243099,0.004120217],"genre_scores_gemma":[0.9110161,0.0002814948,0.08350852,0.00004311492,0.00005899855,0.0002828435,0.004076342,0.00009776711,0.0006347715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01094687,"threshold_uncertainty_score":0.05789328,"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."}}