{"id":"W4409787574","doi":"10.61091/jcmcc127a-364","title":"Improved Web Page Categorization with Semantic-Aware Focused Crawling Using GloVe and TF-IDF","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Categorization; Computer science; Information retrieval; Crawling; World Wide Web; Natural language processing; Artificial intelligence; Medicine","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":[0.000702063,0.000989989,0.001456937,0.004803177,0.000458518,0.001020339,0.0008210337,0.001079413,0.0007219308],"category_scores_gemma":[0.002671857,0.0003205222,0.001466993,0.002624536,0.0002989096,0.002324574,0.0005750835,0.0006752956,0.001215542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005033514,"about_ca_system_score_gemma":0.0008016214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006451005,"about_ca_topic_score_gemma":0.008061461,"domain_scores_codex":[0.9990889,0.0001332506,0.00007899252,0.0002378201,0.0003810891,0.00007993395],"domain_scores_gemma":[0.9985642,0.0003568264,0.0001374317,0.0001981402,0.0006897165,0.00005366574],"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":[0.0002193246,0.0004453306,0.004329609,0.0002252295,0.0001565342,0.0001626596,0.0002118543,0.02076844,0.0511023,0.001134796,0.007323799,0.91392],"study_design_scores_gemma":[0.00004134817,0.0002777027,0.006047087,0.00003529337,0.00009584936,0.000486012,0.0001224856,0.9558622,0.03009195,0.002710712,0.004170195,0.0000592662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1017348,0.001630319,0.8867134,0.0001698289,0.000127623,0.0002285088,0.0005974898,0.007638823,0.001159159],"genre_scores_gemma":[0.35312,0.0008569984,0.6360706,0.000259147,0.0001218716,0.0003206175,0.0036341,0.0003276003,0.005289102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006451005,"threshold_uncertainty_score":0.01282692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01147456424054291,"score_gpt":0.2448094293484025,"score_spread":0.2333348651078596,"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."}}