{"id":"W2046934872","doi":"10.5539/cis.v3n2p268","title":"The Comparison of SOM and K-means for Text Clustering","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Automatic summarization; Cluster analysis; Data mining; Sample (material); Document clustering; Layer (electronics); Information retrieval; Pattern recognition (psychology); Artificial intelligence; Topology (electrical circuits); Mathematics","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":[0.003576085,0.0009967891,0.001221042,0.003463987,0.0007490145,0.001626415,0.001254495,0.001448544,0.002962405],"category_scores_gemma":[0.009307172,0.0003073097,0.0009513714,0.004547249,0.0005389405,0.002487959,0.0008375691,0.000656184,0.00130419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009809233,"about_ca_system_score_gemma":0.0007828719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005042942,"about_ca_topic_score_gemma":0.006603552,"domain_scores_codex":[0.9955475,0.001448291,0.0002303299,0.0004349508,0.002169577,0.0001693049],"domain_scores_gemma":[0.9938203,0.003521878,0.0001755275,0.0004552169,0.001878595,0.0001484869],"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":[0.001850791,0.0002164425,0.004196876,0.001730079,0.0007360586,0.0001433136,0.0004630802,0.1088304,0.008972821,0.01131795,0.006855517,0.8546867],"study_design_scores_gemma":[0.0001670624,0.0006055445,0.009200856,0.0001645414,0.0002203833,0.0004548302,0.0008145305,0.9307131,0.02243117,0.01517291,0.01988992,0.0001651515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07187688,0.009817812,0.8937248,0.0008768234,0.0008423335,0.0003081279,0.0008632509,0.004032684,0.01765721],"genre_scores_gemma":[0.2938237,0.004620987,0.6939581,0.0001534007,0.0003436,0.0002843535,0.001074978,0.0004483002,0.005292592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005042942,"threshold_uncertainty_score":0.01891237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01593078412783907,"score_gpt":0.3185630225082241,"score_spread":0.3026322383803851,"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."}}