{"id":"W4206588201","doi":"10.1109/bigdata52589.2021.9671467","title":"Deep Neural Network to Tradeoff between Accuracy and Diversity in a News Recommender System","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Science and Engineering Research Council","keywords":"Computer science; Recommender system; Representation (politics); Term (time); Reading (process); Artificial intelligence; Information retrieval; Taxonomy (biology); Process (computing); Diversity (politics); Domain (mathematical analysis); Linguistics; Political science","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":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007491137,0.0002691287,0.0003952218,0.000188616,0.0001894928,0.0007682589,0.005519539,0.000114714,0.00003112244],"category_scores_gemma":[0.0001571323,0.0002698357,0.00003524802,0.0004437322,0.00002790894,0.001417909,0.00882978,0.0003686917,0.00003918353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001254104,"about_ca_system_score_gemma":0.0001421114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001098027,"about_ca_topic_score_gemma":0.003176695,"domain_scores_codex":[0.9968293,0.0003039235,0.0005237283,0.001380662,0.0005721425,0.0003902335],"domain_scores_gemma":[0.9963651,0.000313078,0.0001967035,0.002747411,0.0001651055,0.0002125535],"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":[0.00002876529,0.00011175,0.0212538,0.00004891464,0.0001460422,0.0002870512,0.0003527521,0.00003695848,0.00007047675,0.01525007,0.06956485,0.8928486],"study_design_scores_gemma":[0.002942378,0.0003470345,0.05825536,0.001768553,0.00008779301,0.0003142007,0.001460453,0.6399736,0.0005189238,0.004244568,0.2877487,0.002338508],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01034505,0.0001919714,0.941826,0.0265378,0.009979565,0.0007104324,0.003160595,0.0002491283,0.006999493],"genre_scores_gemma":[0.9851333,0.0001805344,0.00949273,0.001124136,0.001370736,0.00001824209,0.002589258,0.00001408395,0.00007695348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9747882,"threshold_uncertainty_score":0.9999754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4290420453509283,"score_gpt":0.3636116226915197,"score_spread":0.06543042265940857,"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."}}