{"id":"W4402265125","doi":"10.1109/tqcebt59414.2024.10545060","title":"Adaptive Web Crawling Strategies Based on Ontological User Interest Modeling for Personalized Content Retrieval","year":2024,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Crawling; Information retrieval; World Wide Web; Web content; Content (measure theory); Web page","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":[0.002069801,0.0006213176,0.0007666529,0.002178873,0.0006949933,0.002135813,0.001142388,0.0008748723,0.0004731858],"category_scores_gemma":[0.007672573,0.00043421,0.0008018994,0.001557359,0.0006783113,0.003477418,0.001196553,0.0009866125,0.0005281417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103898,"about_ca_system_score_gemma":0.001190584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0054769,"about_ca_topic_score_gemma":0.007524477,"domain_scores_codex":[0.9981233,0.0007308964,0.0001489942,0.0003348402,0.0005441894,0.0001176413],"domain_scores_gemma":[0.9969698,0.001237822,0.0002749177,0.0008661557,0.0005531955,0.00009815401],"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":[0.0004578496,0.00121205,0.03132631,0.0004242788,0.0003392179,0.0004650468,0.003346157,0.1573193,0.07857279,0.06025817,0.006763069,0.6595158],"study_design_scores_gemma":[0.00001318702,0.00008766844,0.002562287,0.00001699514,0.00007133228,0.0001728512,0.0001877793,0.9712587,0.01179291,0.009992534,0.003799845,0.00004391311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09056269,0.0003137189,0.9031119,0.0002214827,0.00002165338,0.0002084637,0.0001053497,0.002857867,0.002596801],"genre_scores_gemma":[0.6202447,0.0003055997,0.3766273,0.00008627494,0.00002648518,0.0001949332,0.0004250572,0.0002485392,0.001841247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0054769,"threshold_uncertainty_score":0.01094627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2001224066024497,"score_gpt":0.3218837302668836,"score_spread":0.1217613236644339,"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."}}