{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008666712,0.0007458701,0.0009967012,0.002109692,0.0007836419,0.001418116,0.0009776019,0.001083324,0.003513777],"category_scores_gemma":[0.003241265,0.0002399619,0.0005215617,0.002808749,0.0002747047,0.002007091,0.000853279,0.0004457937,0.002802218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004405321,"about_ca_system_score_gemma":0.0005272336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001392884,"about_ca_topic_score_gemma":0.002052924,"domain_scores_codex":[0.9991622,0.0001384527,0.00005966132,0.0001821261,0.0003781302,0.00007938046],"domain_scores_gemma":[0.9981444,0.0005766308,0.0001118655,0.000231601,0.0008487134,0.00008684856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001725469,0.0007470464,0.002384451,0.0002177924,0.0001261881,0.00008486164,0.0001098066,0.03608695,0.2352073,0.001895042,0.006639301,0.7147759],"study_design_scores_gemma":[0.0001066464,0.0005294052,0.003244906,0.0000118173,0.0001611321,0.0002524345,0.0001518256,0.6825186,0.3067336,0.002440411,0.003799454,0.00004971971],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3521374,0.001567545,0.6241236,0.0003271218,0.0004389032,0.0001572486,0.000328565,0.0118185,0.009101088],"genre_scores_gemma":[0.7075607,0.0003649465,0.2832168,0.0001200435,0.0002126965,0.00007494506,0.001098812,0.0006344296,0.006716539],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003513777,"threshold_uncertainty_score":0.01175475,"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."}}