{"id":"W2885148117","doi":"10.1142/s0219649218500338","title":"High-Dimensional Text Datasets Clustering Algorithm Based on Cuckoo Search and Latent Semantic Indexing","year":2018,"lang":"en","type":"article","venue":"Journal of Information & Knowledge Management","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Concordia University","keywords":"Computer science; Cluster analysis; Cuckoo search; Data mining; Search engine indexing; Document clustering; Clustering high-dimensional data; Curse of dimensionality; Spectral clustering; Artificial intelligence; Machine learning; Particle swarm optimization","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.001138773,0.001313001,0.00171125,0.003801188,0.001959227,0.001516896,0.002921881,0.00145675,0.001817919],"category_scores_gemma":[0.003020142,0.0004133852,0.001277393,0.005769555,0.0007138736,0.002228553,0.001209265,0.001027988,0.0006577114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002727214,"about_ca_system_score_gemma":0.002980187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02611168,"about_ca_topic_score_gemma":0.01822224,"domain_scores_codex":[0.998511,0.0002757668,0.0001355898,0.0003796444,0.0005607132,0.0001372389],"domain_scores_gemma":[0.9990414,0.0002294008,0.0001230251,0.0001054801,0.0004348478,0.00006584978],"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":[0.000311913,0.0002505918,0.003955946,0.0005726625,0.000263109,0.0001835837,0.0004632183,0.6024749,0.008982547,0.03644655,0.01761485,0.3284802],"study_design_scores_gemma":[0.00003279612,0.00003195679,0.0005220553,0.00001277224,0.0000171079,0.0000560495,0.00004713809,0.988887,0.00147094,0.006796111,0.002099723,0.00002637895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04222537,0.001218629,0.9481145,0.0005352135,0.0001310392,0.000539427,0.0007300426,0.001910042,0.00459568],"genre_scores_gemma":[0.4007259,0.00097999,0.58409,0.0002505539,0.0001349544,0.001335292,0.004190778,0.0002922519,0.008000265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02611168,"threshold_uncertainty_score":0.0519194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01674176542965594,"score_gpt":0.2882689026699501,"score_spread":0.2715271372402941,"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."}}