{"id":"W166693255","doi":"10.4018/978-1-60566-172-8.ch009","title":"A Model for Estimating the Savings from Dimensional vs. Keyword Search","year":2009,"lang":"en","type":"book-chapter","venue":"Advances in database research (ADR) book series/Advances in database research series","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Zipf's law; Computer science; Metadata; Keyword search; Process (computing); Information retrieval; Search cost; Search engine; Keyword density; Data mining; Data science; World Wide Web; Economics; Statistics; Mathematics; Microeconomics","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":[0.00432015,0.0008903442,0.001317758,0.002021504,0.0005932573,0.003178366,0.00275094,0.002467114,0.00946746],"category_scores_gemma":[0.03125464,0.000868619,0.00111218,0.003830318,0.001296446,0.007668726,0.00125164,0.001739334,0.002552734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00376783,"about_ca_system_score_gemma":0.001723693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008535706,"about_ca_topic_score_gemma":0.004773639,"domain_scores_codex":[0.9977246,0.0009261548,0.0001291181,0.0004110536,0.0005903229,0.0002187246],"domain_scores_gemma":[0.9749054,0.0208908,0.00166764,0.001091044,0.001207203,0.0002379772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002809482,0.0001205469,0.004081448,0.0001879761,0.00006729778,0.0001310902,0.0001703931,0.8232542,0.001409969,0.1179514,0.003355957,0.04898873],"study_design_scores_gemma":[0.00001922268,0.00006560748,0.0007899153,0.00002001265,0.00003122393,0.0001335426,0.00005909465,0.9592166,0.0004020078,0.03800846,0.001222068,0.00003222845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1027878,0.0009735459,0.8723003,0.001950624,0.00005352675,0.0003230546,0.001413587,0.0009154133,0.019282],"genre_scores_gemma":[0.6909453,0.001454223,0.2870992,0.0004380969,0.00007883176,0.0009131185,0.001530083,0.0003683816,0.01717277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00946746,"threshold_uncertainty_score":0.03167176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08805243973955451,"score_gpt":0.41779534693456,"score_spread":0.3297429071950055,"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."}}