{"id":"W7130592618","doi":"10.1109/fllm67465.2025.11391003","title":"Automated Research Article Classification and Recommendation Using NLP and Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University; York University","funders":"","keywords":"Cosine similarity; Support vector machine; Random forest; Information overload; Complement (music); Statistical classification; Feature extraction; Feature (linguistics)","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":[],"consensus_categories":[],"category_scores_codex":[0.002379487,0.0001779108,0.0002405002,0.0007467402,0.000955042,0.0006822697,0.0002587876,0.0001345905,0.00005311682],"category_scores_gemma":[0.00043467,0.0001821274,0.00002898462,0.002283174,0.000257283,0.001118732,0.0007597211,0.0005482919,0.000007048296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001920935,"about_ca_system_score_gemma":0.00009321614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002759406,"about_ca_topic_score_gemma":0.00006549495,"domain_scores_codex":[0.9973313,0.000735495,0.000480629,0.0007754585,0.0002673754,0.0004097646],"domain_scores_gemma":[0.9985561,0.0003968174,0.0001454359,0.0003918967,0.0004046198,0.0001051184],"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":[0.00002433349,0.0001259212,0.02604958,0.00007711286,0.00006766933,0.000002491045,0.0006836627,0.0002106978,0.09168,0.05175197,0.0002977686,0.8290288],"study_design_scores_gemma":[0.0002377077,0.00007265382,0.01173572,0.0000813493,0.00002758985,0.000005237257,0.0001999937,0.9686329,0.01079304,0.006577934,0.001477983,0.0001578854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1253474,0.000545444,0.8662752,0.004434647,0.00005135367,0.0003109024,7.427864e-7,0.0007528826,0.002281451],"genre_scores_gemma":[0.8878155,0.0005857949,0.1105923,0.00009981488,0.00001387841,0.000009813893,0.000005411566,0.000009772244,0.0008677347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9684222,"threshold_uncertainty_score":0.7426941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1414599886026211,"score_gpt":0.4417872786589687,"score_spread":0.3003272900563476,"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."}}