{"id":"W3034480528","doi":"10.18653/v1/2020.acl-main.514","title":"A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preprocessor; Computer science; Sentiment analysis; Artificial intelligence; Natural language processing; Task (project management); Word (group theory); Data pre-processing; Representation (politics); Task analysis; Support vector machine; Identification (biology); Machine learning; Linguistics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002751164,0.001605485,0.000745815,0.001434748,0.0007541634,0.001775416,0.001098067,0.0009729397,0.006234732],"category_scores_gemma":[0.01743088,0.0004451458,0.001282448,0.001715607,0.0004678314,0.003485817,0.001085594,0.00281334,0.004796246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006453345,"about_ca_system_score_gemma":0.001702261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001925348,"about_ca_topic_score_gemma":0.003931206,"domain_scores_codex":[0.9983719,0.0005953888,0.0001523122,0.000354242,0.0003681166,0.000157986],"domain_scores_gemma":[0.9914851,0.005325634,0.000360564,0.001133827,0.001549503,0.0001453365],"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":[0.0005139133,0.0004702546,0.003043197,0.00070416,0.0001353551,0.00009733374,0.000313902,0.01391231,0.0510668,0.006590722,0.01069361,0.9124584],"study_design_scores_gemma":[0.0001172398,0.001608148,0.02733949,0.0004701659,0.0005276134,0.0005152851,0.001007137,0.6730062,0.1832783,0.05395856,0.05798983,0.0001819719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07467667,0.005560515,0.9056813,0.001394476,0.0004978292,0.0005135027,0.001728691,0.003992694,0.00595443],"genre_scores_gemma":[0.3860445,0.004893622,0.5852512,0.0007761514,0.0003872996,0.001365823,0.0117881,0.001110467,0.008382871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006234732,"threshold_uncertainty_score":0.02085727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06387737328250263,"score_gpt":0.3308107333637708,"score_spread":0.2669333600812681,"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."}}