{"id":"W1523209510","doi":"10.1007/978-3-642-01347-8_28","title":"Enhancing Text Clustering Performance Using Semantic Similarity","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"WordNet; Semantic similarity; Computer science; Cluster analysis; Vector space model; Natural language processing; Explicit semantic analysis; Document clustering; Information retrieval; Artificial intelligence; Ambiguity; Similarity (geometry); Ontology; Semantic computing; Probabilistic latent semantic analysis; Semantic technology; Semantic Web; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003239772,0.0005012506,0.0004659005,0.00100989,0.0003597037,0.000916152,0.001002613,0.0006203901,0.00002261213],"category_scores_gemma":[0.0002165936,0.0004892764,0.0000655441,0.0006466381,0.00009460126,0.005577629,0.000353931,0.0007050206,0.00003822814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003485406,"about_ca_system_score_gemma":0.0003295476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008721501,"about_ca_topic_score_gemma":0.00002925621,"domain_scores_codex":[0.9976503,0.00001125941,0.0009821984,0.000404291,0.0005272499,0.0004246889],"domain_scores_gemma":[0.9978911,0.00006919637,0.0009022757,0.0006414788,0.0004512009,0.00004480548],"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":[0.000007870526,0.000008980331,0.00005408114,0.0007989251,0.000006122762,0.000003116364,0.0005905654,0.0195028,0.0001178665,0.002830438,0.000004576607,0.9760746],"study_design_scores_gemma":[0.0006564297,0.00004724587,0.001296923,0.004754464,0.00004132207,0.00008949819,0.00002210943,0.9349735,0.006390979,0.03217252,0.01783327,0.001721748],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003782366,0.0004814097,0.9837454,0.001020227,0.0002953543,0.0003218594,0.000001745916,0.0006829306,0.01307285],"genre_scores_gemma":[0.8751344,0.0003546074,0.1222192,0.001284046,0.0001564027,0.00001750562,0.00006415505,0.00004692777,0.0007226891],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9743529,"threshold_uncertainty_score":0.9997559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026512744648823,"score_gpt":0.2444281122522229,"score_spread":0.2241629848057347,"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."}}