{"id":"W1594382369","doi":"10.28945/509","title":"HTML Tags as Extraction Cues for Web Page Description Construction","year":2003,"lang":"en","type":"article","venue":"Informing Science The International Journal of an Emerging Transdiscipline","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; World Wide Web; Web page; HTML element","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00146676,0.001265709,0.0005547006,0.008730033,0.0008182594,0.003919614,0.0009463978,0.001652428,0.008063059],"category_scores_gemma":[0.0140832,0.0006249213,0.0007465709,0.005305555,0.000733092,0.005838081,0.002338196,0.001637649,0.008248661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008081124,"about_ca_system_score_gemma":0.001310704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004846279,"about_ca_topic_score_gemma":0.008069942,"domain_scores_codex":[0.9986494,0.0003740121,0.0001741238,0.000257947,0.0003747582,0.0001696978],"domain_scores_gemma":[0.9908497,0.005463512,0.000691069,0.0007802284,0.001875142,0.0003403198],"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":[0.001093533,0.0003559542,0.009916624,0.001899055,0.00009285183,0.001073166,0.002533331,0.003344987,0.06034381,0.01984272,0.05554114,0.8439628],"study_design_scores_gemma":[0.0002744643,0.0005977851,0.03299978,0.001941996,0.0006910979,0.00300767,0.006581457,0.3246654,0.1758034,0.1031232,0.3498513,0.000462435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1083734,0.004998185,0.7927799,0.001946713,0.001372338,0.001191517,0.02170485,0.04166454,0.0259686],"genre_scores_gemma":[0.3601854,0.002483122,0.5819398,0.0004561981,0.0004019976,0.0006420308,0.03751198,0.003590383,0.01278914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008730033,"threshold_uncertainty_score":0.02697361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02587826375411731,"score_gpt":0.3316387600285208,"score_spread":0.3057604962744035,"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."}}