{"id":"W4417312283","doi":"10.18280/isi.301008","title":"Enhancing Sentiment Analysis Accuracy Through Intelligent Spelling Correction Using Damerau-Levenshtein Distance and N-Gram with Random Forest Classifier","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Random forest; Classifier (UML); Sentiment analysis; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143387,0.0009269111,0.0009194635,0.001705511,0.0008334944,0.000964582,0.0005579862,0.0005757142,0.002526246],"category_scores_gemma":[0.003297435,0.0001586305,0.000750536,0.001196454,0.0001755997,0.001283155,0.0005724028,0.0007517561,0.003496695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003335874,"about_ca_system_score_gemma":0.001032093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004681138,"about_ca_topic_score_gemma":0.006978689,"domain_scores_codex":[0.9987411,0.000192803,0.0001511923,0.0002219723,0.0005537272,0.0001392542],"domain_scores_gemma":[0.9976943,0.0004279449,0.0001887209,0.0001711882,0.001459068,0.000058702],"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":[0.0004215901,0.0002522918,0.004395155,0.0001577198,0.00008131773,0.0001690341,0.0001026646,0.003942176,0.1305419,0.0007109881,0.008632634,0.8505926],"study_design_scores_gemma":[0.00006065176,0.0004568015,0.01410916,0.00005330595,0.0001996318,0.0005673477,0.0002639391,0.7605972,0.2096022,0.002303401,0.01169937,0.00008707307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2188396,0.001254166,0.7620445,0.0006010968,0.0008296804,0.0002094363,0.001275181,0.009524183,0.005422089],"genre_scores_gemma":[0.4931254,0.0005331037,0.4940874,0.000191495,0.0002433172,0.0001093927,0.003507024,0.0005266139,0.007676359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004681138,"threshold_uncertainty_score":0.009307802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02123104573779639,"score_gpt":0.2740604898328334,"score_spread":0.252829444095037,"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."}}