{"id":"W4309811661","doi":"10.1016/j.mex.2022.101935","title":"An automated method for developing search strategies for systematic review using Natural Language Processing (NLP)","year":2022,"lang":"en","type":"article","venue":"MethodsX","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Forest Service","funders":"","keywords":"Computer science; Python (programming language); Data deduplication; Software; Systematic review; Data mining; Information retrieval; Artificial intelligence; Natural language processing; Machine learning; Database; Programming language","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003318622,0.000147244,0.0003735057,0.00003564535,0.000610831,0.00009872469,0.0003150451,0.00002961674,0.00116962],"category_scores_gemma":[0.0002021794,0.000127992,0.00009610418,0.0004104438,0.00004519788,0.0002539648,0.0001381531,0.000105278,0.000006260856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000786753,"about_ca_system_score_gemma":0.00006005314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009013141,"about_ca_topic_score_gemma":0.00001680614,"domain_scores_codex":[0.9980291,0.0006815388,0.0003238239,0.0003178247,0.0003013988,0.000346384],"domain_scores_gemma":[0.9993249,0.0002297758,0.0001490293,0.00021112,0.0000331637,0.00005199707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001929919,0.0003887965,0.0001519428,0.5856744,0.0001823833,0.00002702421,0.01927633,0.004160493,0.3484202,0.007447676,0.003914785,0.03016294],"study_design_scores_gemma":[0.0005787282,0.0001426645,0.0001768013,0.004402938,0.0002537096,0.00008461026,0.04907802,0.9387565,0.004442255,0.0003407003,0.001134227,0.0006088656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01749458,0.007120324,0.9699949,0.0004029217,0.0001853561,0.003854785,0.0001848986,0.0004291806,0.0003330349],"genre_scores_gemma":[0.0441272,0.00002606904,0.9526727,0.001435745,0.00002980884,0.001292511,0.0002255577,0.00004230069,0.0001480845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.934596,"threshold_uncertainty_score":0.9997435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1108296255897259,"score_gpt":0.4701853592969272,"score_spread":0.3593557337072013,"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."}}