{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000436235,0.0001604874,0.0002192889,0.000150993,0.0001070814,0.0007784617,0.0004980773,0.00007023577,0.00004023186],"category_scores_gemma":[0.00009723156,0.0001115632,0.0002083263,0.0002647045,0.00003953345,0.0004399473,0.00008499839,0.000163513,0.00002764097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098404,"about_ca_system_score_gemma":0.0001744352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004675514,"about_ca_topic_score_gemma":0.00004677208,"domain_scores_codex":[0.998682,0.00005696926,0.0002267285,0.0005619359,0.0002155141,0.0002568189],"domain_scores_gemma":[0.9991189,0.0003783262,0.00002715516,0.0002956301,0.0001023756,0.00007767759],"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":[0.0003720521,0.0001526602,0.00003281981,0.00006200028,0.0002235093,0.00008927288,0.000692694,0.03070614,0.005124594,0.9569259,0.001607041,0.004011262],"study_design_scores_gemma":[0.0003235794,0.000257636,0.000002648761,0.000100035,0.00002727528,0.000002726719,0.0009299296,0.9958104,0.0002740959,0.0009961294,0.001113239,0.0001623171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01952066,0.0001219227,0.9762102,0.001741882,0.000206495,0.0001059803,0.0000223567,0.000356092,0.001714397],"genre_scores_gemma":[0.9478392,0.000003920145,0.05037696,0.0003993311,0.00007441627,0.00001141832,0.00001430533,0.000008451115,0.001272011],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9651042,"threshold_uncertainty_score":0.7506724,"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."}}