{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001369893,0.0001795265,0.0002154723,0.0009098146,0.0002581233,0.0003605226,0.0007170047,0.00004710256,0.00002263374],"category_scores_gemma":[0.00004111828,0.000151967,0.00005247591,0.0005009657,0.00008157192,0.002017281,0.00100907,0.0003083618,0.00018839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002240796,"about_ca_system_score_gemma":0.00007110302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005310465,"about_ca_topic_score_gemma":0.000002537737,"domain_scores_codex":[0.9978285,0.00009183825,0.0006581564,0.0001757756,0.0008860579,0.0003596182],"domain_scores_gemma":[0.9986027,0.00009286125,0.0002463877,0.0004075363,0.000460866,0.0001896699],"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":[0.00005777767,0.0001048245,0.00001944296,0.0001577889,0.0000639499,0.0000499489,0.0006897099,0.03406537,0.00001853963,0.001340037,0.002003305,0.9614293],"study_design_scores_gemma":[0.001288293,0.0004533297,0.001295069,0.0002923121,0.000009419645,0.00006280241,0.0000861102,0.988217,0.000374596,0.0001347886,0.007624578,0.0001617182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001959572,0.00003632704,0.9950625,0.0005255831,0.0006738861,0.0002383356,0.000009082132,0.00003824191,0.001456443],"genre_scores_gemma":[0.3598001,0.00004559239,0.6388693,0.0006480594,0.0003603907,0.00001031447,0.00002501441,0.00001794333,0.000223325],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9612676,"threshold_uncertainty_score":0.6197034,"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."}}