{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003260649,0.0000506678,0.00006289416,0.00006937912,0.0005157794,0.0002941435,0.0004646089,0.00001616873,1.906161e-7],"category_scores_gemma":[0.00002390669,0.00003642717,0.00001286059,0.0002526281,0.0002860119,0.002434583,0.0002716399,0.00006105709,8.496493e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004469321,"about_ca_system_score_gemma":0.00003743922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001217501,"about_ca_topic_score_gemma":0.000001432566,"domain_scores_codex":[0.9994174,0.000003113379,0.0002148418,0.0001051936,0.0001491205,0.0001103474],"domain_scores_gemma":[0.9992862,0.0001552125,0.000113813,0.0001897457,0.0002064671,0.00004861313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.709838e-7,0.000004115385,0.00007906866,0.000006582196,6.563027e-7,4.09906e-9,0.000591429,0.0006460724,0.0005043453,0.5248674,0.00007403798,0.4732253],"study_design_scores_gemma":[0.00008190225,0.00003808858,0.00344133,0.000003960398,5.885855e-7,0.000005268887,0.00002239198,0.9497072,0.001100968,0.008362447,0.03718597,0.00004985654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007185225,0.00001213527,0.9912814,0.0007672468,0.0001383534,0.0001711775,0.000001632402,0.00004114394,0.000401714],"genre_scores_gemma":[0.5382385,0.00001076109,0.461544,0.0001690856,0.0000173907,0.0000157223,7.315967e-7,8.181901e-7,0.000002989338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9490612,"threshold_uncertainty_score":0.396701,"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."}}