{"id":"W4387099797","doi":"10.54254/2755-2721/6/20230334","title":"Feature selection in text classification: Identifying spurious words with causal inference methods","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spurious relationship; Computer science; Inference; Causal inference; Artificial intelligence; Weighting; Feature selection; Feature (linguistics); Machine learning; Propensity score matching; Matching (statistics); Selection (genetic algorithm); Model selection; Selection bias; Pattern recognition (psychology); Data mining; Statistics; Mathematics","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":[0.01619757,0.00132642,0.001657499,0.003510684,0.001200226,0.001966701,0.002140406,0.001578097,0.001584898],"category_scores_gemma":[0.04581133,0.0004714626,0.001488499,0.002987245,0.001469186,0.003620595,0.002178256,0.003069283,0.0006830097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009037137,"about_ca_system_score_gemma":0.001748253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001542151,"about_ca_topic_score_gemma":0.001938693,"domain_scores_codex":[0.9909156,0.005219587,0.0006386349,0.001649433,0.001254798,0.000321977],"domain_scores_gemma":[0.9667639,0.02392734,0.002600528,0.004510113,0.001844213,0.000353926],"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":[0.0007139641,0.0007318093,0.04228601,0.0004996766,0.0006325414,0.0005730531,0.0008109833,0.1056334,0.007108908,0.0414546,0.008191219,0.7913637],"study_design_scores_gemma":[0.00009673784,0.0001269235,0.003842483,0.00006918857,0.000110763,0.0001374838,0.0001019128,0.89302,0.004092844,0.09591518,0.002445032,0.0000413132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02512864,0.0006808767,0.9721273,0.0006091623,0.00007989365,0.0001069624,0.0001370716,0.0008314564,0.0002985329],"genre_scores_gemma":[0.6933064,0.0005338066,0.3026274,0.00059034,0.0004023744,0.0004027253,0.0009721573,0.0001417995,0.001023056],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01619757,"threshold_uncertainty_score":0.08566195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02398821052233942,"score_gpt":0.3065342753834491,"score_spread":0.2825460648611097,"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."}}