{"id":"W4301605997","doi":"10.23889/ijpds.v7i1.1757","title":"A scoping review of preprocessing methods for unstructured text data to assess data quality","year":2022,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canada Research Chairs","keywords":"Computer science; Preprocessor; Punctuation; Data quality; Data pre-processing; Stop words; Information retrieval; Lexical analysis; Natural language processing; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.1192936,0.0003425022,0.00166487,0.001138523,0.0007887261,0.0021249,0.0544372,0.00007620063,0.0004184565],"category_scores_gemma":[0.1551206,0.0002622833,0.0002218469,0.002136638,0.0001927214,0.009437866,0.02545096,0.0003545998,0.000007443812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766372,"about_ca_system_score_gemma":0.002754723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000859502,"about_ca_topic_score_gemma":0.0000698519,"domain_scores_codex":[0.9858254,0.001375292,0.004651135,0.002719895,0.005014746,0.0004135255],"domain_scores_gemma":[0.9694701,0.008737557,0.007315258,0.01208978,0.002060535,0.0003268091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001638609,0.00003557527,0.000003198368,0.01516574,0.00007216633,7.113733e-7,0.00001581812,0.00001734407,9.618203e-7,0.001280966,0.01433392,0.9690572],"study_design_scores_gemma":[0.0001476429,0.00002282537,0.00001462649,0.06427237,0.0002488629,0.00004923794,0.00005719169,0.003803544,4.46795e-7,0.002534024,0.9285659,0.0002832889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.775133e-7,0.5087191,0.459062,0.0005346828,0.003809113,0.001991975,0.0258214,0.00001273481,0.00004884132],"genre_scores_gemma":[7.113046e-7,0.6736616,0.2973722,0.0004914062,0.0003421187,0.00006211572,0.02794647,0.00001974873,0.000103668],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9687739,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9239911994930267,"score_gpt":0.7624971008446532,"score_spread":0.1614940986483735,"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."}}