{"id":"W2025470942","doi":"10.1016/j.asoc.2015.02.029","title":"Automated classification and localization of daily deal content from the Web","year":2015,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; News aggregator; Discriminative model; Web page; Set (abstract data type); Information retrieval; Web content; Machine learning; World Wide Web; Artificial intelligence","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":[0.0002757254,0.0003754327,0.0004353182,0.009697383,0.0003914237,0.001429235,0.0004615234,0.0007533948,0.002112721],"category_scores_gemma":[0.001806262,0.0001916165,0.0003725878,0.004538731,0.0002217756,0.001236987,0.0006729836,0.0004733974,0.002743289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003457704,"about_ca_system_score_gemma":0.0004890488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004677871,"about_ca_topic_score_gemma":0.007616804,"domain_scores_codex":[0.9996507,0.00004371725,0.00002533207,0.00008549257,0.0001367586,0.00005789325],"domain_scores_gemma":[0.9986216,0.0004252262,0.0002567289,0.0001650621,0.0004138196,0.0001175181],"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":[0.0009440174,0.0007906524,0.2476444,0.0005046845,0.0001588554,0.0009593197,0.0007137305,0.008855276,0.05577772,0.002278464,0.0298188,0.6515541],"study_design_scores_gemma":[0.0000357303,0.0001624077,0.3663776,0.00008507472,0.0001310951,0.001086694,0.001344135,0.5774578,0.02984875,0.004842944,0.01856562,0.00006204666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9335356,0.001448353,0.04286743,0.0004070467,0.0000942961,0.0001577926,0.01079375,0.004458992,0.006236801],"genre_scores_gemma":[0.9435714,0.0005969545,0.0336896,0.0000551451,0.0001598421,0.00008223611,0.0155036,0.0001900762,0.006151206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009697383,"threshold_uncertainty_score":0.009301245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06116658146903416,"score_gpt":0.2576346301896803,"score_spread":0.1964680487206462,"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."}}