{"id":"W2906685695","doi":"10.1007/s10115-018-1278-7","title":"Combining semantic and term frequency similarities for text clustering","year":2019,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Semantic similarity; Computer science; Document clustering; Similarity (geometry); Measure (data warehouse); Information retrieval; Similarity measure; Natural language processing; Term (time); Artificial intelligence; Word (group theory); Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002037002,0.00008688413,0.0001329152,0.0001565243,0.0001212954,0.000478067,0.000189652,0.00006488503,0.00000164935],"category_scores_gemma":[0.00002247297,0.00007590689,0.00001730354,0.000104048,0.00002688438,0.003214444,0.0001270655,0.00004718287,0.00005420994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001730461,"about_ca_system_score_gemma":0.00001856013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005474195,"about_ca_topic_score_gemma":0.000001559079,"domain_scores_codex":[0.9994033,0.00001202534,0.0002782558,0.0001083929,0.00007038647,0.0001276316],"domain_scores_gemma":[0.9994855,0.00007406912,0.0001155796,0.0002066783,0.00008834455,0.00002982253],"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":[0.00000482765,0.00001657308,0.01269581,0.00156468,0.00002436229,1.436937e-7,0.01122626,0.00001200933,0.0005755522,0.8524855,0.001452804,0.1199415],"study_design_scores_gemma":[0.00280395,0.0004499895,0.02152757,0.0006493693,0.00001723673,0.00006820701,0.008267388,0.757913,0.001084672,0.004126457,0.2022596,0.0008325913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1304501,0.003670856,0.7936513,0.0008219174,0.002156708,0.001895438,0.00001355896,0.00107316,0.06626697],"genre_scores_gemma":[0.9980265,0.00007045909,0.001292695,0.00004641076,0.00001734803,0.00005807085,0.000006893855,0.000002890264,0.0004786649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8675765,"threshold_uncertainty_score":0.4610011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01570786528100131,"score_gpt":0.2428618567949933,"score_spread":0.227153991513992,"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."}}